
import numpy as np
import pandas as pd
import random
pd.set_option('display.max_columns',None)
import sklearn
import seaborn as sns
import matplotlib.pyplot as plt
%matplotlib inline
from sklearn.metrics import roc_auc_score, roc_curve, auc
from imblearn.over_sampling import SMOTE
from imblearn.under_sampling import RandomUnderSampler
from sklearn.datasets import make_classification
from sklearn.metrics import classification_report
from imblearn.over_sampling import RandomOverSampler

seed_value = 1234


#Carreguem el Train set
train_df = pd.read_csv('C:/Users/Ramon/Documents/TFM/dataset/aps_failure_training_set_processed_8bit.csv', na_values=["NaN"]).sample(frac=1, random_state=seed_value)
train_df.head()


#Carreguem el Test set
test_df = pd.read_csv('C:/Users/Ramon/Documents/TFM/dataset/aps_failure_test_set_processed_8bit.csv', na_values=["NaN"]).sample(frac=1, random_state=seed_value)
test_df.head()


print("Dimensions del train set: " + str(test_df.shape))

Dimensions del train set: (16000, 171)


combined_df = pd.concat([train_df, test_df])


null_counts = combined_df.isnull().sum()
columnesAmbNulls = null_counts[null_counts > 0]
print("Columnes amb algún valor nul:")
print(columnesAmbNulls)

Columnes amb algún valor nul:
Series([], dtype: int64)


combined_df.info()

<class 'pandas.core.frame.DataFrame'>
Index: 76000 entries, 0 to 15999
Columns: 171 entries, class to eg_000
dtypes: float64(171)
memory usage: 99.7 MB


combined_df.describe()


#Arrodonim els valors de class a 1 o -1, per evitar valors decimals.
train_df['class'] = train_df['class'].round().replace(-1, 0).replace(-1, 0)
test_df['class'] = test_df['class'].round().replace(-1, 0)
train_df['class'] = train_df['class'].astype(int)
test_df['class'] = test_df['class'].astype(int)


sns.barplot(data=combined_df,x=combined_df['class'].unique(),y=combined_df['class'].value_counts())

<Axes: ylabel='count'>


pos = combined_df['class'].round().value_counts().get(1, 0)
neg = combined_df['class'].round().replace(-1, 0).value_counts().get(0, 0)
perc = pos/neg*100
print("Núm valors '1':", pos, ", Núm valors '0':", neg, " Perc. positius:", round(perc,2),"%")

Núm valors '1': 1375 , Núm valors '0': 74625  Perc. positius: 1.84 %


correlation_matrix = combined_df.corr()
class_correlation = correlation_matrix['class']
sorted_correlation = class_correlation.abs().sort_values(ascending=False)
top_correlated_variables = sorted_correlation[0:11].index
top_correlated_variables = top_correlated_variables.tolist()
filtered_correlation_matrix = correlation_matrix.loc[top_correlated_variables, top_correlated_variables]
sns.set(style="white")
mask = np.triu(np.ones_like(filtered_correlation_matrix, dtype=bool))
plt.figure(figsize=(6, 6))
sns.heatmap(filtered_correlation_matrix, mask=mask, annot=True, cmap="coolwarm", fmt=".2f")
plt.show()


sns.pairplot(combined_df, vars=top_correlated_variables)

C:\Users\Ramon\anaconda3\Lib\site-packages\seaborn\axisgrid.py:118: UserWarning: The figure layout has changed to tight
  self._figure.tight_layout(*args, **kwargs)

<seaborn.axisgrid.PairGrid at 0x25bbc1ae790>


rows_p = combined_df[combined_df['class'] >0]
rows_n = combined_df[combined_df['class'] < 0]


abs_p = rows_p['ag_002'].abs()
ave_p = abs_p.mean()
median_p = abs_p.median()
std_p = abs_p.std()

# Display the results
print("Casos positius")
print(f"Average (absolute): {ave_p}")
print(f"Median: {median_p}")
print(f"Standard Deviation: {std_p}\n\n")

abs_n = rows_n['ag_002'].abs()
ave_n = abs_n.mean()
median_n = abs_n.median()
std_n = abs_n.std()

print("Casos negatius")
print(f"Average (absolute): {ave_n}")
print(f"Median: {median_n}")
print(f"Standard Deviation: {std_n}")

Casos positius
Average (absolute): 0.4271193181818182
Median: 0.0546875
Standard Deviation: 0.4413658887175721


Casos negatius
Average (absolute): 0.05892033082077052
Median: 0.0546875
Standard Deviation: 0.0568288713371542


fig, axs = plt.subplots(4, 2, figsize=(12, 16))

axs[0][0].hist(rows_p['ag_002'], bins=50, color='red', alpha=0.7)
axs[0][0].set_title('Distribució dels positius (ag_002)')
axs[0][0].set_xlabel('Positius')
axs[0][0].set_ylabel('Freqüència')
axs[0][1].hist(rows_n['ag_002'], bins=50, color='green', alpha=0.7)
axs[0][1].set_title('Distribució dels negatius (ag_002)')
axs[0][1].set_xlabel('Negatius')
axs[0][1].set_ylabel('Freqüència')

axs[1][0].hist(rows_p['az_000'], bins=50, color='red', alpha=0.7)
axs[1][0].set_title('Distribució dels positius (az_000)')
axs[1][0].set_xlabel('Positius')
axs[1][0].set_ylabel('Freqüència')
axs[1][1].hist(rows_n['az_000'], bins=50, color='green', alpha=0.7)
axs[1][1].set_title('Distribució dels negatius (az_000)')
axs[1][1].set_xlabel('Negatius')
axs[1][1].set_ylabel('Freqüència')

axs[2][0].hist(rows_p['az_002'], bins=50, color='red', alpha=0.7)
axs[2][0].set_title('Distribució dels positius (az_002)')
axs[2][0].set_xlabel('Positius')
axs[2][0].set_ylabel('Freqüència')
axs[2][1].hist(rows_n['az_002'], bins=50, color='green', alpha=0.7)
axs[2][1].set_title('Distribució dels negatius (az_002)')
axs[2][1].set_xlabel('Negatius')
axs[2][1].set_ylabel('Freqüència')

axs[3][0].hist(rows_p['cn_000'], bins=50, color='red', alpha=0.7)
axs[3][0].set_title('Distribució dels positius (cn_000)')
axs[3][0].set_xlabel('Positius')
axs[3][0].set_ylabel('Freqüència')
axs[3][1].hist(rows_n['cn_000'], bins=50, color='green', alpha=0.7)
axs[3][1].set_title('Distribució dels negatius (cn_000)')
axs[3][1].set_xlabel('Negatius')
axs[3][1].set_ylabel('Freqüència')

plt.tight_layout()
plt.show()


y_train = train_df['class'].copy()
X_train = train_df.drop(['class'],axis=1).copy()
y_test = test_df['class'].copy()
X_test = test_df.drop(['class'],axis=1).copy()


X = pd.concat([X_train, X_test])
y = pd.concat([y_train, y_test])


# Utilitzem RandomUnderSampler amb la finalitat de reduir el número de mostres de la classe majoritària
rus = RandomUnderSampler(sampling_strategy=0.2, random_state=seed_value)
X_resampled, y_resampled = rus.fit_resample(X_train, y_train)

# Utilitzem SMOTE amb la finalitat d'augmentar el número de mostres de la classe minoritària
#smote = SMOTE(sampling_strategy='auto', random_state=seed_value)
#X_resampled, y_resampled = smote.fit_resample(X_resampled, y_resampled)
ros = RandomOverSampler(sampling_strategy='auto', random_state=seed_value)
X_resampled, y_resampled = ros.fit_resample(X_resampled, y_resampled)


rus = RandomUnderSampler(sampling_strategy=0.2, random_state=seed_value)
X_res, y_res = rus.fit_resample(X, y)

# Utilitzem SMOTE amb la finalitat d'augmentar el número de mostres de la classe minoritària
#smote = SMOTE(sampling_strategy='auto', random_state=seed_value)
#X_resampled, y_resampled = smote.fit_resample(X_resampled, y_resampled)
ros = RandomOverSampler(sampling_strategy='auto', random_state=seed_value)
X_res, y_res = ros.fit_resample(X_res, y_res)


print("Nombre de mostres positives:", sum(y_resampled == 1))
print("Nombre de mostres negatives:", sum(y_resampled == 0))

Nombre de mostres positives: 5000
Nombre de mostres negatives: 5000


from collections import Counter
from sklearn.ensemble import RandomForestClassifier
from sklearn.feature_selection import RFE
from sklearn.metrics import confusion_matrix
from sklearn.metrics import accuracy_score
from sklearn.metrics import recall_score, balanced_accuracy_score, f1_score, precision_score, accuracy_score
#Funció per calcular la matriu de confusió, la precisió, el recall i el F1
def calcularQualitatResultats(y_test, y_pred):
    confusion_mat = confusion_matrix(y_test, y_pred)
    confusion_mat_inverted = confusion_mat[::-1, ::-1]
    print(confusion_mat_inverted)
    
    precision = precision_score(y_test, y_pred)
    print(f'Precision: {round(precision, 3)}')
    
    accuracy = accuracy_score(y_test, y_pred)
    print(f'Accuracy: {round(accuracy, 3)}')

    recall = recall_score(y_test, y_pred)
    print(f'Recall: {round(recall, 3)}')
    
    f1 = f1_score(y_test, y_pred, labels=[1], average='micro')
    print(f'F1: {round(f1, 3)}')


from sklearn.model_selection import cross_val_score

def calcularValidacioCreuada(model, x, y):
    cv_scores = cross_val_score(model, x, y, cv=5, scoring='recall')
    print("Scores de validació creuada (recall):", cv_scores)
    print("Mitjana dels scores (recall):", cv_scores.mean())
    cv_scores = cross_val_score(model, x, y, cv=5, scoring='f1')
    print("Scores de validació creuada (f1):", cv_scores)
    print("Mitjana dels scores (f1):", cv_scores.mean())


top_correlated_variables = top_correlated_variables[1:11]


from sklearn.model_selection import GridSearchCV

param_grid = {'n_estimators': [50, 100, 200],
              'max_depth': [None, 10, 20, 30]}

grid_search = GridSearchCV(RandomForestClassifier(random_state=seed_value), param_grid, cv=5)
grid_search.fit(X[top_correlated_variables], y)
print("Millors paràmetres trobats a través de Grid Search:")
print(grid_search.best_params_)

Millors paràmetres trobats a través de Grid Search:
{'max_depth': 20, 'n_estimators': 100}


grid_search = GridSearchCV(RandomForestClassifier(random_state=seed_value), param_grid, cv=5)
grid_search.fit(X_res[top_correlated_variables], y_res)
print("Millors paràmetres trobats a través de Grid Search:")
print(grid_search.best_params_)

Millors paràmetres trobats a través de Grid Search:
{'max_depth': None, 'n_estimators': 100}


# Entrenem amb les variables més correlacionades
model_rfc = RandomForestClassifier(random_state=seed_value,class_weight={0: 0.98, 1: 0.02})
#model_rfc.fit(X_train[top_correlated_variables], y_train)
#y_pred = model_rfc.predict(X_test[top_correlated_variables])
#calcularQualitatResultats(y_test, y_pred)


calcularValidacioCreuada(model_rfc, X[top_correlated_variables], y)

Scores de validació creuada (recall): [0.49454545 0.46545455 0.42545455 0.49818182 0.52      ]
Mitjana dels scores (recall): 0.4807272727272728
Scores de validació creuada (f1): [0.60176991 0.5577342  0.54418605 0.59956236 0.62582057]
Mitjana dels scores (f1): 0.5858146189950766


#Entrenem amb max_depth=20
model_rfc = RandomForestClassifier(random_state=seed_value,class_weight={0: 0.98, 1: 0.02}, max_depth=20)
#model_rfc.fit(X_train[top_correlated_variables], y_train)
#y_pred = model_rfc.predict(X_test[top_correlated_variables])
#calcularQualitatResultats(y_test, y_pred)
calcularValidacioCreuada(model_rfc, X[top_correlated_variables], y)

Scores de validació creuada (recall): [0.42909091 0.37090909 0.35636364 0.39636364 0.45818182]
Mitjana dels scores (recall): 0.40218181818181814
Scores de validació creuada (f1): [0.55924171 0.49514563 0.49122807 0.52403846 0.59294118]
Mitjana dels scores (f1): 0.5325190090827173


model_rfc_resampling = RandomForestClassifier(random_state=seed_value)
#model_rfc_resampling.fit(X_resampled[top_correlated_variables], y_resampled)
#y_pred = model_rfc_resampling.predict(X_test[top_correlated_variables])
#calcularQualitatResultats(y_test, y_pred)
calcularValidacioCreuada(model_rfc_resampling, X_res[top_correlated_variables], y_res)

Scores de validació creuada (recall): [0.99418182 0.99781818 0.99272727 0.99636364 0.99563636]
Mitjana dels scores (recall): 0.9953454545454546
Scores de validació creuada (f1): [0.98098314 0.98175313 0.97360913 0.97997139 0.982771  ]
Mitjana dels scores (f1): 0.9798175563872986


#Mostrem un simple arbre de decisió per obtenir una mostra visual
from sklearn.tree import DecisionTreeClassifier, plot_tree
import matplotlib.pyplot as plt

model_dt = DecisionTreeClassifier(random_state=seed_value)
model_dt.fit(X[top_correlated_variables], y)

plt.figure(figsize=(12, 8))
plot_tree(model_dt, filled=True, feature_names=top_correlated_variables, class_names=["Negatiu", "Positiu"], rounded=True)
plt.show()


#Mostrem un simple arbre de decisió per obtenir una mostra visual amb SAMPLING
from sklearn.tree import DecisionTreeClassifier, plot_tree
import matplotlib.pyplot as plt

model_dt_resampling = DecisionTreeClassifier(random_state=seed_value)
model_dt_resampling.fit(X_res[top_correlated_variables], y_res)

plt.figure(figsize=(12, 8))
plot_tree(model_dt_resampling, filled=True, feature_names=top_correlated_variables, class_names=["Negatiu", "Positiu"], rounded=True)
plt.show()


#Entrenem amb les variables més importants trobades durant l'entrenament
tmp = RandomForestClassifier(random_state=seed_value)
tmp.fit(X, y)

feature_importance = tmp.feature_importances_
feature_ranking = sorted(zip(feature_importance, X_train.columns), reverse=True)

for importance, feature in feature_ranking[:20]:
    print(f'{feature}: {importance}')

aq_000: 0.03859702646103143
ag_002: 0.038109633323867007
ag_001: 0.03681617357229708
ap_000: 0.03152896997784845
bj_000: 0.026646179157282082
dn_000: 0.026132009097502244
cn_000: 0.023751866925356125
ck_000: 0.02020124709693456
bh_000: 0.019129322753020418
ay_005: 0.017189392835597176
ai_000: 0.015381877476428978
az_002: 0.014815515057561863
ay_006: 0.013731624733032657
az_000: 0.013580614631730034
bk_000: 0.013115031158206412
az_001: 0.012420981375734797
aa_000: 0.012033814175385696
cs_002: 0.012033651116092997
am_0: 0.011548522552351361
bb_000: 0.010681172815911157


#Entrenem amb les variables més importants trobades durant l'entrenament
tmp = RandomForestClassifier(random_state=seed_value)
tmp.fit(X_res, y_res)

feature_importance_sampling = tmp.feature_importances_
feature_ranking_sampling = sorted(zip(feature_importance_sampling, X_resampled.columns), reverse=True)

for importance, feature in feature_ranking_sampling[:20]:
    print(f'{feature}: {importance}')

ap_000: 0.08458694779793273
dn_000: 0.07467220850740514
bt_000: 0.06503089099465721
aa_000: 0.060021924069825074
bb_000: 0.04808749844273397
ci_000: 0.04334849542532763
ck_000: 0.043266593945758026
bv_000: 0.03658317213071928
bj_000: 0.03526801400239967
bh_000: 0.0344362316041101
ah_000: 0.03219006177139122
bu_000: 0.03215038108719533
aq_000: 0.02490782481520959
bx_000: 0.022013141177277748
bi_000: 0.021951071384568796
az_000: 0.017016968591169076
bg_000: 0.015944205105030827
ba_002: 0.01557171127840761
cs_002: 0.014912900287000392
cq_000: 0.011393214548399217


top_10_features = [feature for importance, feature in feature_ranking[:10]]


top_10_features_sampling = [feature for importance, feature in feature_ranking_sampling[:10]]


#Cerquem quin és el nombre òptim d'estimadors
from sklearn.metrics import f1_score
from collections import OrderedDict
from sklearn.ensemble import RandomForestClassifier

ensemble_clfs = [ ("RandomForestClassifier, max_features=None",RandomForestClassifier(warm_start=True, max_features=None, oob_score=True,))]
error_rate = OrderedDict((label, []) for label, _ in ensemble_clfs)
estimators = [10,20,30,50,100,300,500]
f1_scores = {}

for label, clf in ensemble_clfs:
    f1_scores[label] = []
    for i in estimators:
        clf.set_params(n_estimators=i)
        clf.fit(X_train[top_10_features], y_train)  # Train on your training data, not X_test
        y_pred = clf.predict(X_test[top_10_features])
        f1 = f1_score(y_test, y_pred, labels=[1], average='micro')  # You can choose 'micro' or 'macro' depending on your needs
        f1_scores[label].append((i, f1))

for label, clf_err in f1_scores.items():
    xs, ys = zip(*clf_err)
    plt.plot(xs, ys, label=label)

plt.xlim(0, 500)
plt.xlabel("n_estimators")
plt.ylabel("F1 Score")
plt.legend(loc="upper right")
plt.show()

C:\Users\Ramon\anaconda3\Lib\site-packages\sklearn\ensemble\_forest.py:578: UserWarning: Some inputs do not have OOB scores. This probably means too few trees were used to compute any reliable OOB estimates.
  warn(
C:\Users\Ramon\anaconda3\Lib\site-packages\sklearn\ensemble\_forest.py:578: UserWarning: Some inputs do not have OOB scores. This probably means too few trees were used to compute any reliable OOB estimates.
  warn(


model_rfc2 = RandomForestClassifier(random_state=seed_value, class_weight={0: 0.98, 1: 0.02})
#model_rfc2.fit(X_train[top_10_features], y_train)
#y_pred = model_rfc2.predict(X_test[top_10_features])
#calcularQualitatResultats(y_test, y_pred)
calcularValidacioCreuada(model_rfc2, X[top_10_features], y)

Scores de validació creuada (recall): [0.41090909 0.41090909 0.39636364 0.44       0.43272727]
Mitjana dels scores (recall): 0.41818181818181815
Scores de validació creuada (f1): [0.5368171  0.53809524 0.52278177 0.56018519 0.55868545]
Mitjana dels scores (f1): 0.5433129492015831


model_rfc2_resampling = RandomForestClassifier(random_state=seed_value)
#model_rfc2_resampling.fit(X_resampled[top_10_features_sampling], y_resampled)
#y_pred = model_rfc2_resampling.predict(X_test[top_10_features_sampling])
#calcularQualitatResultats(y_test, y_pred)
calcularValidacioCreuada(model_rfc2_resampling, X_res[top_10_features_sampling], y_res)

Scores de validació creuada (recall): [0.99490909 0.99854545 0.99781818 0.99636364 0.99781818]
Mitjana dels scores (recall): 0.997090909090909
Scores de validació creuada (f1): [0.98134864 0.97896613 0.97512438 0.97787295 0.98175313]
Mitjana dels scores (f1): 0.9790130451034489


#PCA
from sklearn.decomposition import PCA
pca = PCA(n_components=10, random_state=seed_value)
X_train_pca = pca.fit_transform(X_train)
X_test_pca = pca.transform(X_test)
X_pca = pca.fit_transform(X)


from sklearn.decomposition import PCA
pca = PCA(n_components=10, random_state=seed_value)
X_resampled_pca = pca.fit_transform(X_resampled)
X_res_pca = pca.fit_transform(X_res)


model_rfc3 = RandomForestClassifier(random_state=seed_value)
#model_rfc3.fit(X_train_pca, y_train)
#y_pred = model_rfc3.predict(X_test_pca)
#calcularQualitatResultats(y_test, y_pred)
calcularValidacioCreuada(model_rfc3, X_pca, y)

Scores de validació creuada (recall): [0.33090909 0.31636364 0.31272727 0.34909091 0.42181818]
Mitjana dels scores (recall): 0.3461818181818182
Scores de validació creuada (f1): [0.45614035 0.45430809 0.43877551 0.47058824 0.50877193]
Mitjana dels scores (f1): 0.4657168240389463


#Entrenem amb PCA i SAMPLING
model_rfc3_resampling = RandomForestClassifier(random_state=seed_value)
#model_rfc3_resampling.fit(X_resampled_pca[:10000], y_resampled)
#y_pred = model_rfc3_resampling.predict(X_test_pca)
#calcularQualitatResultats(y_test, y_pred)
calcularValidacioCreuada(model_rfc3_resampling, X_res_pca, y_res)

Scores de validació creuada (recall): [0.99854545 1.         1.         1.         1.        ]
Mitjana dels scores (recall): 0.9997090909090909
Scores de validació creuada (f1): [0.97896613 0.97621583 0.97552324 0.97795164 0.98039216]
Mitjana dels scores (f1): 0.9778097984504148


import xgboost as xgb
from xgboost import XGBClassifier
from sklearn.metrics import confusion_matrix

xgb_classifier = XGBClassifier(n_estimators=100, objective="binary:logistic", seed=seed_value)
#y_pred_prob = model.predict(dtest)
#y_pred = [1 if prob >= 0.15 else 0 for prob in y_pred_prob]
calcularValidacioCreuada(xgb_classifier, X, y)

Scores de validació creuada (recall): [0.69454545 0.69090909 0.78909091 0.76727273 0.77454545]
Mitjana dels scores (recall): 0.7432727272727273
Scores de validació creuada (f1): [0.77800407 0.77393075 0.8460039  0.82101167 0.80834915]
Mitjana dels scores (f1): 0.8054599089562393


xgb_classifier = XGBClassifier(n_estimators=100, objective="binary:logistic", seed=seed_value)
#y_pred_prob = model.predict(dtest)
#y_pred = [1 if prob >= 0.15 else 0 for prob in y_pred_prob]
calcularValidacioCreuada(xgb_classifier, X_res, y_res)

Scores de validació creuada (recall): [0.99709091 1.         1.         1.         1.        ]
Mitjana dels scores (recall): 0.9994181818181819
Scores de validació creuada (f1): [0.98597627 0.98743268 0.98284489 0.98920863 0.99170573]
Mitjana dels scores (f1): 0.9874336397473786


from sklearn.naive_bayes import GaussianNB

model_nb = GaussianNB()
#model_nb.fit(X_train[top_correlated_variables], y_train)
#y_pred_nb = model_nb.predict(X_test[top_correlated_variables])
#calcularQualitatResultats(y_test, y_pred_nb)
calcularValidacioCreuada(model_nb, X[top_correlated_variables], y)

Scores de validació creuada (recall): [0.85454545 0.82909091 0.88727273 0.84727273 0.89818182]
Mitjana dels scores (recall): 0.8632727272727273
Scores de validació creuada (f1): [0.38461538 0.39790576 0.42324371 0.40985048 0.44107143]
Mitjana dels scores (f1): 0.4113373536267472


model_nb_resampling = GaussianNB()
model_nb_resampling.fit(X_resampled, y_resampled)
#y_pred_nb = model_nb_resampling.predict(X_test[top_correlated_variables])
#calcularQualitatResultats(y_test, y_pred_nb)
calcularValidacioCreuada(model_nb_resampling, X_res, y_res)

Scores de validació creuada (recall): [0.94254545 0.96363636 0.93527273 0.94181818 0.93890909]
Mitjana dels scores (recall): 0.9444363636363636
Scores de validació creuada (f1): [0.93270961 0.93905032 0.92484718 0.92998205 0.93618564]
Mitjana dels scores (f1): 0.9325549584835452


from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score, classification_report
import numpy as np

model_lr = LogisticRegression()
#model_lr.fit(X_train, y_train)
#y_pred = model_lr.predict(X_test[top_correlated_variables])
#calcularQualitatResultats(y_test, y_pred)
calcularValidacioCreuada(model_lr, X[top_correlated_variables], y)

Scores de validació creuada (recall): [0.34909091 0.29454545 0.31636364 0.31272727 0.33818182]
Mitjana dels scores (recall): 0.3221818181818182
Scores de validació creuada (f1): [0.45933014 0.41968912 0.44615385 0.45263158 0.47328244]
Mitjana dels scores (f1): 0.4502174261121922


model_lr_resampling = LogisticRegression()
#model_lr_resampling.fit(X_resampled[top_correlated_variables], y_resampled)
#y_pred = model_lr_resampling.predict(X_test[top_correlated_variables])
#calcularQualitatResultats(y_test, y_pred)
calcularValidacioCreuada(model_lr_resampling, X_res[top_correlated_variables], y_res)

Scores de validació creuada (recall): [0.93527273 0.94909091 0.92654545 0.93309091 0.936     ]
Mitjana dels scores (recall): 0.9360000000000002
Scores de validació creuada (f1): [0.94385321 0.94496741 0.93230882 0.94130594 0.94424065]
Mitjana dels scores (f1): 0.9413352064964761


import warnings
warnings.filterwarnings("ignore", category=UserWarning, module="sklearn.metrics")
from sklearn.svm import SVC
from sklearn.model_selection import GridSearchCV
from sklearn.metrics import make_scorer


# Primer obtindrem només quins són els millors hiperparàmetres per entrenar el SVC

svm = SVC(random_state=seed_value)

param_grid = {
    'kernel': ['linear', 'poly', 'rbf', 'sigmoid'],
    'C': [0.1, 1, 10],
    'degree': [2, 3, 4],  # Només per al nucli polinòmic
    'gamma': ['scale', 'auto', 0.1, 1]  # Només per als nuclis rbf, poly, i sigmoid
}

scoring = {
    'precision': make_scorer(precision_score),
    'recall': make_scorer(recall_score),
    'f1': make_scorer(f1_score)
}

print("GridSearchCV")
grid_search = GridSearchCV(svm, param_grid, scoring=scoring, refit='f1', cv=5)
print("fit")
grid_search.fit(X_train[top_correlated_variables][:3000], y_train[:3000]) # utilitzem només 3000 registres perquè no tardi massa
best_svm_model = grid_search.best_estimator_
print("Millors hiperparàmetres:")
print(grid_search.best_params_)

GridSearchCV
fit
Millors hiperparàmetres:
{'C': 1, 'degree': 4, 'gamma': 1, 'kernel': 'poly'}


svm_model = SVC(C=1, degree=4, gamma=1, kernel='poly', random_state=seed_value)
#svm_model.fit(X_train, y_train)
#y_pred = svm_model.predict(X_test)
#calcularQualitatResultats(y_test, y_pred)
calcularValidacioCreuada(svm_model, X[top_correlated_variables], y)

Scores de validació creuada (recall): [0.36363636 0.30909091 0.30909091 0.28363636 0.36727273]
Mitjana dels scores (recall): 0.3265454545454545
Scores de validació creuada (f1): [0.50505051 0.44270833 0.45092838 0.42276423 0.51530612]
Mitjana dels scores (f1): 0.4673515140875918


svm_model_resampling = SVC(C=1, degree=4, gamma=1, kernel='poly', random_state=seed_value)
#svm_model.fit(X_resampled, y_resampled)
#y_pred = svm_model.predict(X_test)
#calcularQualitatResultats(y_test, y_pred)
calcularValidacioCreuada(svm_model_resampling, X_res[top_correlated_variables], y_res)

Scores de validació creuada (recall): [0.93163636 0.94327273 0.91781818 0.936      0.928     ]
Mitjana dels scores (recall): 0.9313454545454546
Scores de validació creuada (f1): [0.94888889 0.94809942 0.93377728 0.94493392 0.94518519]
Mitjana dels scores (f1): 0.9441769388964607


import tensorflow as tf
from sklearn.metrics import confusion_matrix, precision_score, recall_score, f1_score
from tensorflow.keras import backend as K

def f1_metric(y_true, y_pred):
    y_pred = K.round(y_pred)
    precision = K.sum(y_true * y_pred) / (K.sum(y_pred) + K.epsilon())
    recall = K.sum(y_true * y_pred) / (K.sum(y_true) + K.epsilon())
    f1 = 2 * (precision * recall) / (precision + recall + K.epsilon())
    return f1

model = tf.keras.Sequential([
    tf.keras.layers.Dense(64, activation='relu', input_shape=(X_train.shape[1],)),
    tf.keras.layers.Dense(32, activation='relu'),
    tf.keras.layers.Dense(1, activation='sigmoid')
])

# Compile the model
model.compile(optimizer='adam', loss='binary_crossentropy', metrics=[tf.keras.metrics.Recall(), f1_metric])

# Train the model
model.fit(X_train, y_train, epochs=20, batch_size=32, validation_data=(X_test, y_test))

# Make predictions on the test set
y_pred_prob = model.predict(X_test)
y_pred = [1 if prob >= 0.5 else 0 for prob in y_pred_prob]

# Evaluate the quality of the results using your function
calcularQualitatResultats(y_test, y_pred)

WARNING:tensorflow:From C:\Users\Ramon\anaconda3\Lib\site-packages\keras\src\backend.py:873: The name tf.get_default_graph is deprecated. Please use tf.compat.v1.get_default_graph instead.

WARNING:tensorflow:From C:\Users\Ramon\anaconda3\Lib\site-packages\keras\src\optimizers\__init__.py:309: The name tf.train.Optimizer is deprecated. Please use tf.compat.v1.train.Optimizer instead.

Epoch 1/20
WARNING:tensorflow:From C:\Users\Ramon\anaconda3\Lib\site-packages\keras\src\utils\tf_utils.py:492: The name tf.ragged.RaggedTensorValue is deprecated. Please use tf.compat.v1.ragged.RaggedTensorValue instead.

WARNING:tensorflow:From C:\Users\Ramon\anaconda3\Lib\site-packages\keras\src\engine\base_layer_utils.py:384: The name tf.executing_eagerly_outside_functions is deprecated. Please use tf.compat.v1.executing_eagerly_outside_functions instead.

1875/1875 [==============================] - 4s 2ms/step - loss: 0.0347 - recall: 0.5150 - f1_metric: 0.2146 - val_loss: 0.0302 - val_recall: 0.5627 - val_f1_metric: 0.3247
Epoch 2/20
1875/1875 [==============================] - 3s 1ms/step - loss: 0.0244 - recall: 0.6520 - f1_metric: 0.2748 - val_loss: 0.0273 - val_recall: 0.6773 - val_f1_metric: 0.3852
Epoch 3/20
1875/1875 [==============================] - 3s 1ms/step - loss: 0.0220 - recall: 0.6830 - f1_metric: 0.2824 - val_loss: 0.0275 - val_recall: 0.6347 - val_f1_metric: 0.3625
Epoch 4/20
1875/1875 [==============================] - 3s 1ms/step - loss: 0.0208 - recall: 0.6910 - f1_metric: 0.2863 - val_loss: 0.0285 - val_recall: 0.6160 - val_f1_metric: 0.3456
Epoch 5/20
1875/1875 [==============================] - 3s 1ms/step - loss: 0.0195 - recall: 0.7160 - f1_metric: 0.2965 - val_loss: 0.0280 - val_recall: 0.5947 - val_f1_metric: 0.3383
Epoch 6/20
1875/1875 [==============================] - 3s 1ms/step - loss: 0.0188 - recall: 0.7250 - f1_metric: 0.3052 - val_loss: 0.0272 - val_recall: 0.7547 - val_f1_metric: 0.4103
Epoch 7/20
1875/1875 [==============================] - 3s 1ms/step - loss: 0.0177 - recall: 0.7420 - f1_metric: 0.3110 - val_loss: 0.0335 - val_recall: 0.5680 - val_f1_metric: 0.3249
Epoch 8/20
1875/1875 [==============================] - 3s 1ms/step - loss: 0.0164 - recall: 0.7620 - f1_metric: 0.3136 - val_loss: 0.0283 - val_recall: 0.6880 - val_f1_metric: 0.3830
Epoch 9/20
1875/1875 [==============================] - 3s 1ms/step - loss: 0.0155 - recall: 0.7740 - f1_metric: 0.3297 - val_loss: 0.0314 - val_recall: 0.6507 - val_f1_metric: 0.3647
Epoch 10/20
1875/1875 [==============================] - 3s 1ms/step - loss: 0.0146 - recall: 0.7930 - f1_metric: 0.3327 - val_loss: 0.0324 - val_recall: 0.6773 - val_f1_metric: 0.3756
Epoch 11/20
1875/1875 [==============================] - 3s 1ms/step - loss: 0.0139 - recall: 0.8030 - f1_metric: 0.3277 - val_loss: 0.0354 - val_recall: 0.6160 - val_f1_metric: 0.3499
Epoch 12/20
1875/1875 [==============================] - 3s 1ms/step - loss: 0.0126 - recall: 0.8130 - f1_metric: 0.3306 - val_loss: 0.0350 - val_recall: 0.6453 - val_f1_metric: 0.3605
Epoch 13/20
1875/1875 [==============================] - 3s 1ms/step - loss: 0.0123 - recall: 0.8310 - f1_metric: 0.3447 - val_loss: 0.0364 - val_recall: 0.6960 - val_f1_metric: 0.3823
Epoch 14/20
1875/1875 [==============================] - 3s 1ms/step - loss: 0.0117 - recall: 0.8170 - f1_metric: 0.3441 - val_loss: 0.0378 - val_recall: 0.6267 - val_f1_metric: 0.3517
Epoch 15/20
1875/1875 [==============================] - 3s 1ms/step - loss: 0.0112 - recall: 0.8300 - f1_metric: 0.3392 - val_loss: 0.0365 - val_recall: 0.7360 - val_f1_metric: 0.3979
Epoch 16/20
1875/1875 [==============================] - 3s 1ms/step - loss: 0.0102 - recall: 0.8430 - f1_metric: 0.3554 - val_loss: 0.0393 - val_recall: 0.6880 - val_f1_metric: 0.3825
Epoch 17/20
1875/1875 [==============================] - 3s 1ms/step - loss: 0.0102 - recall: 0.8490 - f1_metric: 0.3622 - val_loss: 0.0393 - val_recall: 0.7333 - val_f1_metric: 0.3954
Epoch 18/20
1875/1875 [==============================] - 3s 1ms/step - loss: 0.0096 - recall: 0.8610 - f1_metric: 0.3534 - val_loss: 0.0419 - val_recall: 0.7173 - val_f1_metric: 0.3888
Epoch 19/20
1875/1875 [==============================] - 3s 1ms/step - loss: 0.0094 - recall: 0.8690 - f1_metric: 0.3609 - val_loss: 0.0420 - val_recall: 0.6853 - val_f1_metric: 0.3773
Epoch 20/20
1875/1875 [==============================] - 3s 1ms/step - loss: 0.0089 - recall: 0.8700 - f1_metric: 0.3536 - val_loss: 0.0413 - val_recall: 0.8027 - val_f1_metric: 0.4238
500/500 [==============================] - 1s 909us/step
[[  301    74]
 [  114 15511]]
Precision: 0.725
Accuracy: 0.988
Recall: 0.803
F1: 0.762


import tensorflow as tf
from sklearn.metrics import confusion_matrix, precision_score, recall_score, f1_score
from tensorflow.keras import backend as K

def f1_metric(y_true, y_pred):
    y_pred = K.round(y_pred)
    precision = K.sum(y_true * y_pred) / (K.sum(y_pred) + K.epsilon())
    recall = K.sum(y_true * y_pred) / (K.sum(y_true) + K.epsilon())
    f1 = 2 * (precision * recall) / (precision + recall + K.epsilon())
    return f1

model = tf.keras.Sequential([
    tf.keras.layers.Dense(64, activation='relu', input_shape=(X_train.shape[1],)),
    tf.keras.layers.Dense(32, activation='relu'),
    tf.keras.layers.Dense(1, activation='sigmoid')
])

# Compile the model
model.compile(optimizer='adam', loss='binary_crossentropy', metrics=[tf.keras.metrics.Recall(), f1_metric])

# Train the model
model.fit(X_resampled, y_resampled, epochs=20, batch_size=32, validation_data=(X_test, y_test))

# Make predictions on the test set
y_pred_prob = model.predict(X_test)
y_pred = [1 if prob >= 0.5 else 0 for prob in y_pred_prob]

# Evaluate the quality of the results using your function
calcularQualitatResultats(y_test, y_pred)

WARNING:tensorflow:From C:\Users\Ramon\anaconda3\Lib\site-packages\keras\src\losses.py:2976: The name tf.losses.sparse_softmax_cross_entropy is deprecated. Please use tf.compat.v1.losses.sparse_softmax_cross_entropy instead.

WARNING:tensorflow:From C:\Users\Ramon\anaconda3\Lib\site-packages\keras\src\backend.py:873: The name tf.get_default_graph is deprecated. Please use tf.compat.v1.get_default_graph instead.

WARNING:tensorflow:From C:\Users\Ramon\anaconda3\Lib\site-packages\keras\src\optimizers\__init__.py:309: The name tf.train.Optimizer is deprecated. Please use tf.compat.v1.train.Optimizer instead.

Epoch 1/20
WARNING:tensorflow:From C:\Users\Ramon\anaconda3\Lib\site-packages\keras\src\utils\tf_utils.py:492: The name tf.ragged.RaggedTensorValue is deprecated. Please use tf.compat.v1.ragged.RaggedTensorValue instead.

WARNING:tensorflow:From C:\Users\Ramon\anaconda3\Lib\site-packages\keras\src\engine\base_layer_utils.py:384: The name tf.executing_eagerly_outside_functions is deprecated. Please use tf.compat.v1.executing_eagerly_outside_functions instead.

313/313 [==============================] - 2s 4ms/step - loss: 0.1734 - recall: 0.9580 - f1_metric: 0.9442 - val_loss: 0.1179 - val_recall: 0.9733 - val_f1_metric: 0.3632
Epoch 2/20
313/313 [==============================] - 1s 3ms/step - loss: 0.1059 - recall: 0.9754 - f1_metric: 0.9674 - val_loss: 0.1317 - val_recall: 0.9840 - val_f1_metric: 0.3772
Epoch 3/20
313/313 [==============================] - 1s 3ms/step - loss: 0.0904 - recall: 0.9800 - f1_metric: 0.9736 - val_loss: 0.1152 - val_recall: 0.9787 - val_f1_metric: 0.3921
Epoch 4/20
313/313 [==============================] - 1s 3ms/step - loss: 0.0767 - recall: 0.9818 - f1_metric: 0.9780 - val_loss: 0.0979 - val_recall: 0.9653 - val_f1_metric: 0.4058
Epoch 5/20
313/313 [==============================] - 1s 3ms/step - loss: 0.0668 - recall: 0.9848 - f1_metric: 0.9807 - val_loss: 0.1165 - val_recall: 0.9680 - val_f1_metric: 0.3923
Epoch 6/20
313/313 [==============================] - 1s 3ms/step - loss: 0.0604 - recall: 0.9858 - f1_metric: 0.9825 - val_loss: 0.0753 - val_recall: 0.9360 - val_f1_metric: 0.4211
Epoch 7/20
313/313 [==============================] - 1s 3ms/step - loss: 0.0568 - recall: 0.9870 - f1_metric: 0.9839 - val_loss: 0.0669 - val_recall: 0.9200 - val_f1_metric: 0.4210
Epoch 8/20
313/313 [==============================] - 1s 3ms/step - loss: 0.0449 - recall: 0.9902 - f1_metric: 0.9884 - val_loss: 0.0661 - val_recall: 0.9093 - val_f1_metric: 0.4222
Epoch 9/20
313/313 [==============================] - 1s 3ms/step - loss: 0.0418 - recall: 0.9900 - f1_metric: 0.9887 - val_loss: 0.1172 - val_recall: 0.9467 - val_f1_metric: 0.4030
Epoch 10/20
313/313 [==============================] - 1s 3ms/step - loss: 0.0380 - recall: 0.9896 - f1_metric: 0.9897 - val_loss: 0.1209 - val_recall: 0.9493 - val_f1_metric: 0.3943
Epoch 11/20
313/313 [==============================] - 1s 3ms/step - loss: 0.0329 - recall: 0.9912 - f1_metric: 0.9917 - val_loss: 0.1479 - val_recall: 0.9627 - val_f1_metric: 0.3951
Epoch 12/20
313/313 [==============================] - 1s 3ms/step - loss: 0.0300 - recall: 0.9904 - f1_metric: 0.9913 - val_loss: 0.1436 - val_recall: 0.9387 - val_f1_metric: 0.3944
Epoch 13/20
313/313 [==============================] - 1s 4ms/step - loss: 0.0269 - recall: 0.9914 - f1_metric: 0.9923 - val_loss: 0.1675 - val_recall: 0.9573 - val_f1_metric: 0.3926
Epoch 14/20
313/313 [==============================] - 1s 4ms/step - loss: 0.0252 - recall: 0.9906 - f1_metric: 0.9923 - val_loss: 0.0990 - val_recall: 0.8987 - val_f1_metric: 0.4081
Epoch 15/20
313/313 [==============================] - 1s 4ms/step - loss: 0.0212 - recall: 0.9926 - f1_metric: 0.9936 - val_loss: 0.1406 - val_recall: 0.9307 - val_f1_metric: 0.4055
Epoch 16/20
313/313 [==============================] - 1s 3ms/step - loss: 0.0196 - recall: 0.9930 - f1_metric: 0.9945 - val_loss: 0.1548 - val_recall: 0.9307 - val_f1_metric: 0.4011
Epoch 17/20
313/313 [==============================] - 1s 3ms/step - loss: 0.0192 - recall: 0.9926 - f1_metric: 0.9942 - val_loss: 0.1182 - val_recall: 0.9040 - val_f1_metric: 0.4138
Epoch 18/20
313/313 [==============================] - 1s 3ms/step - loss: 0.0211 - recall: 0.9904 - f1_metric: 0.9925 - val_loss: 0.1221 - val_recall: 0.9227 - val_f1_metric: 0.4012
Epoch 19/20
313/313 [==============================] - 1s 3ms/step - loss: 0.0174 - recall: 0.9938 - f1_metric: 0.9951 - val_loss: 0.1927 - val_recall: 0.9413 - val_f1_metric: 0.3965
Epoch 20/20
313/313 [==============================] - 1s 4ms/step - loss: 0.0166 - recall: 0.9936 - f1_metric: 0.9954 - val_loss: 0.1259 - val_recall: 0.8933 - val_f1_metric: 0.4174
500/500 [==============================] - 1s 1ms/step
[[  335    40]
 [  312 15313]]
Precision: 0.518
Accuracy: 0.978
Recall: 0.893
F1: 0.656


from sklearn.cluster import KMeans
from sklearn.metrics import silhouette_score, davies_bouldin_score
n_clusters = 2
X_test_array = X_test.values
kmeans = KMeans(n_clusters=n_clusters, random_state=42)
kmeans.fit(X_test_array)

cluster_labels = kmeans.labels_

silhouette_avg = silhouette_score(X_test_array, cluster_labels)
print(f"Silhouette Score: {silhouette_avg}")

db_index = davies_bouldin_score(X_test_array, cluster_labels)
print(f"Davies–Bouldin Index: {db_index}")

plt.scatter(X_test_array[:, 0], X_test_array[:, 1], c=cluster_labels, cmap='viridis', marker='o', edgecolors='k', s=50)
plt.scatter(kmeans.cluster_centers_[:, 0], kmeans.cluster_centers_[:, 1], c='red', marker='X', s=200, label='Centroids')
plt.title('K-means Clustering')
plt.xlabel('Feature 1')
plt.ylabel('Feature 2')
plt.legend()
plt.show()

C:\Users\Ramon\anaconda3\Lib\site-packages\sklearn\cluster\_kmeans.py:1412: FutureWarning: The default value of `n_init` will change from 10 to 'auto' in 1.4. Set the value of `n_init` explicitly to suppress the warning
  super()._check_params_vs_input(X, default_n_init=10)

Silhouette Score: 0.340885971110426
Davies–Bouldin Index: 0.9948450984993457


from sklearn.metrics import adjusted_rand_score,normalized_mutual_info_score, homogeneity_score, completeness_score, v_measure_score

ari_score = adjusted_rand_score(y_test, cluster_labels)
print(f"Adjusted Rand Index: {ari_score}")
nmi_score = normalized_mutual_info_score(y_test, cluster_labels)
print(f"Normalized Mutual Information: {nmi_score}")
homogeneity = homogeneity_score(y_test, cluster_labels)
completeness = completeness_score(y_test, cluster_labels)
v_measure = v_measure_score(y_test, cluster_labels)

print(f"Homogeneity: {homogeneity}")
print(f"Completeness: {completeness}")
print(f"V-measure: {v_measure}")

Adjusted Rand Index: -0.022208038473670887
Normalized Mutual Information: 0.023753658721748883
Homogeneity: 0.07881608863354447
Completeness: 0.01398409910362346
V-measure: 0.023753658721748887


from sklearn.cluster import DBSCAN
from sklearn.preprocessing import StandardScaler
import matplotlib.pyplot as plt

dbscan_model = DBSCAN(eps=0.85, min_samples=30)  # You can adjust eps and min_samples
dbscan_model.fit(X_train)
predictions_dbscan = dbscan_model.fit_predict(X_test)
X_test_array = X_test.values

plt.scatter(X_test_array[:, 0], X_test_array[:, 1], c=predictions_dbscan, cmap='viridis', marker='o', edgecolors='k', s=50)
plt.title('DBSCAN Clustering')
plt.xlabel('Feature 1 (Scaled)')
plt.ylabel('Feature 2 (Scaled)')
plt.show()


from sklearn.metrics import calinski_harabasz_score
silhouette_avg = silhouette_score(X_test, predictions_dbscan)
print(f"Silhouette Score: {silhouette_avg}")
davies_bouldin = davies_bouldin_score(X_test, predictions_dbscan)
print(f"Davies-Bouldin Index: {davies_bouldin}")
calinski_harabasz = calinski_harabasz_score(X_test, predictions_dbscan)
print(f"Calinski-Harabasz Index: {calinski_harabasz}")
unique_clusters, cluster_counts = np.unique(predictions_dbscan, return_counts=True)
cluster_density = dict(zip(unique_clusters, cluster_counts))
print("Cluster Density:", cluster_density)

Silhouette Score: 0.008660676244886333
Davies-Bouldin Index: 1.6874120150000287
Calinski-Harabasz Index: 1885.685098754403
Cluster Density: {-1: 9856, 0: 4277, 1: 1655, 2: 131, 3: 50, 4: 31}


dbscan_model = DBSCAN(eps=0.85, min_samples=30)  # You can adjust eps and min_samples
dbscan_model.fit(X_resampled)
predictions_dbscan = dbscan_model.fit_predict(X_test)
X_test_array = X_test.values

plt.scatter(X_test_array[:, 0], X_test_array[:, 1], c=predictions_dbscan, cmap='viridis', marker='o', edgecolors='k', s=50)
plt.title('DBSCAN Clustering')
plt.xlabel('Feature 1 (Scaled)')
plt.ylabel('Feature 2 (Scaled)')
plt.show()


from sklearn.metrics import calinski_harabasz_score
silhouette_avg = silhouette_score(X_test, predictions_dbscan)
print(f"Silhouette Score: {silhouette_avg}")
davies_bouldin = davies_bouldin_score(X_test, predictions_dbscan)
print(f"Davies-Bouldin Index: {davies_bouldin}")
calinski_harabasz = calinski_harabasz_score(X_test, predictions_dbscan)
print(f"Calinski-Harabasz Index: {calinski_harabasz}")
unique_clusters, cluster_counts = np.unique(predictions_dbscan, return_counts=True)
cluster_density = dict(zip(unique_clusters, cluster_counts))
print("Cluster Density:", cluster_density)

Silhouette Score: 0.008660676244886333
Davies-Bouldin Index: 1.6874120150000287
Calinski-Harabasz Index: 1885.685098754403
Cluster Density: {-1: 9856, 0: 4277, 1: 1655, 2: 131, 3: 50, 4: 31}


from sklearn.ensemble import IsolationForest
from sklearn.datasets import make_blobs
model_if = IsolationForest(contamination=0.04, random_state=seed_value)
#model_if.fit(X_train)
#predictions = model_if.predict(X_test)
#print("Predictions:", predictions)
#print(".............")
#predictions = np.where(predictions == -1, 0, predictions)
#predictions = 1-predictions
#calcularQualitatResultats(y_test, predictions)
predictions = np.where(y == 0, -1, y)
calcularValidacioCreuada(model_if, X[top_correlated_variables], predictions)

Scores de validació creuada (recall): [0.22957198 0.29482072 0.27272727 0.30078125 0.23184358]
Mitjana dels scores (recall): 0.2659489599427078
Scores de validació creuada (f1): [0.00796598 0.00994691 0.00926672 0.01035225 0.01114468]
Mitjana dels scores (f1): 0.009735305180520277


from sklearn.ensemble import IsolationForest
from sklearn.datasets import make_blobs
model_if_resampling = IsolationForest(contamination=0.04, random_state=seed_value)
model_if_resampling.fit(X_resampled)

#predictions = model_if_resampling.predict(X_test)
#print("Predictions:", predictions)
#print(".............")
#predictions = np.where(predictions == -1, 0, predictions)
#predictions = 1-predictions
#calcularQualitatResultats(y_test, predictions)
predictions = np.where(y_res == 0, -1, y_res)
calcularValidacioCreuada(model_if_resampling, X_res[top_correlated_variables], predictions)

Scores de validació creuada (recall): [0.         0.         0.93236364 0.89345455 0.89345455]
Mitjana dels scores (recall): 0.5438545454545455
Scores de validació creuada (f1): [0.         0.         0.63686041 0.94372959 0.94372959]
Mitjana dels scores (f1): 0.5048639193809472


from sklearn.neighbors import LocalOutlierFactor
lof_model = LocalOutlierFactor(contamination='auto',novelty=True) 
#lof_model.fit(X_train)
#predictions_lof = lof_model.fit_predict(X_test)
#predictions_lof_mapped = np.where(predictions_lof == -1, 0, 1)

#print("LOF Predictions:", predictions_lof_mapped)
#calcularQualitatResultats(y_test, predictions_lof_mapped)
predictions_train_mapped = np.where(y_train == 0, -1, 1)
calcularValidacioCreuada(lof_model, X_train[top_correlated_variables], predictions_train_mapped)

C:\Users\Ramon\anaconda3\Lib\site-packages\sklearn\base.py:464: UserWarning: X does not have valid feature names, but LocalOutlierFactor was fitted with feature names
  warnings.warn(
C:\Users\Ramon\anaconda3\Lib\site-packages\sklearn\base.py:464: UserWarning: X does not have valid feature names, but LocalOutlierFactor was fitted with feature names
  warnings.warn(
C:\Users\Ramon\anaconda3\Lib\site-packages\sklearn\base.py:464: UserWarning: X does not have valid feature names, but LocalOutlierFactor was fitted with feature names
  warnings.warn(
C:\Users\Ramon\anaconda3\Lib\site-packages\sklearn\base.py:464: UserWarning: X does not have valid feature names, but LocalOutlierFactor was fitted with feature names
  warnings.warn(
C:\Users\Ramon\anaconda3\Lib\site-packages\sklearn\base.py:464: UserWarning: X does not have valid feature names, but LocalOutlierFactor was fitted with feature names
  warnings.warn(

Scores de validació creuada (recall): [0.84649123 0.8372093  0.82474227 0.89673913 0.82681564]
Mitjana dels scores (recall): 0.8463995142659755

C:\Users\Ramon\anaconda3\Lib\site-packages\sklearn\base.py:464: UserWarning: X does not have valid feature names, but LocalOutlierFactor was fitted with feature names
  warnings.warn(
C:\Users\Ramon\anaconda3\Lib\site-packages\sklearn\base.py:464: UserWarning: X does not have valid feature names, but LocalOutlierFactor was fitted with feature names
  warnings.warn(
C:\Users\Ramon\anaconda3\Lib\site-packages\sklearn\base.py:464: UserWarning: X does not have valid feature names, but LocalOutlierFactor was fitted with feature names
  warnings.warn(
C:\Users\Ramon\anaconda3\Lib\site-packages\sklearn\base.py:464: UserWarning: X does not have valid feature names, but LocalOutlierFactor was fitted with feature names
  warnings.warn(
C:\Users\Ramon\anaconda3\Lib\site-packages\sklearn\base.py:464: UserWarning: X does not have valid feature names, but LocalOutlierFactor was fitted with feature names
  warnings.warn(

Scores de validació creuada (f1): [0.0330791  0.03089864 0.02751032 0.02821236 0.0253794 ]
Mitjana dels scores (f1): 0.02901596344898318


lof_model = LocalOutlierFactor(contamination='auto') 
lof_model.fit(X_train)
predictions_lof = lof_model.fit_predict(X_test)
predictions_lof_mapped = np.where(predictions_lof == -1, 0, 1)

X, _ = make_blobs(n_samples=16000, centers=1, random_state=42)
plt.scatter(X[predictions_lof_mapped == 1, 0], X[predictions_lof_mapped == 1, 1], c='blue', label='Outliers', edgecolors='k', s=50)
plt.scatter(X[predictions_lof_mapped == 0, 0], X[predictions_lof_mapped == 0, 1], c='red', label='Inliers', edgecolors='k', s=50)
plt.title("One-Class SVM Outlier Detection")
plt.legend()
plt.show()


from sklearn.neighbors import LocalOutlierFactor
lof_model_resampling = LocalOutlierFactor(contamination='auto', novelty=True) 
#lof_model_resampling.fit(X_resampled)
#predictions_lof_resampling = lof_model_resampling.fit_predict(X_test)
#predictions_lof_mapped_resampling = np.where(predictions_lof_resampling == -1, 0, 1)
#print("LOF Predictions:", predictions_lof_mapped_resampling)
#calcularQualitatResultats(y_test, predictions_lof_mapped_resampling)
predictions_train_mapped = np.where(y_resampled == 0, -1, 1)
calcularValidacioCreuada(lof_model_resampling, X_resampled[top_correlated_variables], predictions_train_mapped)

C:\Users\Ramon\anaconda3\Lib\site-packages\sklearn\base.py:464: UserWarning: X does not have valid feature names, but LocalOutlierFactor was fitted with feature names
  warnings.warn(
C:\Users\Ramon\anaconda3\Lib\site-packages\sklearn\base.py:464: UserWarning: X does not have valid feature names, but LocalOutlierFactor was fitted with feature names
  warnings.warn(
C:\Users\Ramon\anaconda3\Lib\site-packages\sklearn\base.py:464: UserWarning: X does not have valid feature names, but LocalOutlierFactor was fitted with feature names
  warnings.warn(
C:\Users\Ramon\anaconda3\Lib\site-packages\sklearn\base.py:464: UserWarning: X does not have valid feature names, but LocalOutlierFactor was fitted with feature names
  warnings.warn(
C:\Users\Ramon\anaconda3\Lib\site-packages\sklearn\base.py:464: UserWarning: X does not have valid feature names, but LocalOutlierFactor was fitted with feature names
  warnings.warn(

Scores de validació creuada (recall): [0.     0.     0.88   0.8605 0.889 ]
Mitjana dels scores (recall): 0.5259

C:\Users\Ramon\anaconda3\Lib\site-packages\sklearn\base.py:464: UserWarning: X does not have valid feature names, but LocalOutlierFactor was fitted with feature names
  warnings.warn(
C:\Users\Ramon\anaconda3\Lib\site-packages\sklearn\base.py:464: UserWarning: X does not have valid feature names, but LocalOutlierFactor was fitted with feature names
  warnings.warn(
C:\Users\Ramon\anaconda3\Lib\site-packages\sklearn\base.py:464: UserWarning: X does not have valid feature names, but LocalOutlierFactor was fitted with feature names
  warnings.warn(
C:\Users\Ramon\anaconda3\Lib\site-packages\sklearn\base.py:464: UserWarning: X does not have valid feature names, but LocalOutlierFactor was fitted with feature names
  warnings.warn(

Scores de validació creuada (f1): [0.         0.         0.63791229 0.92502016 0.94123875]
Mitjana dels scores (f1): 0.5008342387188665

C:\Users\Ramon\anaconda3\Lib\site-packages\sklearn\base.py:464: UserWarning: X does not have valid feature names, but LocalOutlierFactor was fitted with feature names
  warnings.warn(


from sklearn.svm import OneClassSVM
svm_model = OneClassSVM(nu=0.5)  # Adjust the nu parameter based on your dataset
#svm_model.fit(X_train)

#predictions_svm = svm_model.predict(X_test)
#predictions_svm_mapped = np.where(predictions_svm == -1, 0, 1)

#print("One-Class SVM Predictions:", predictions_svm_mapped)
#calcularQualitatResultats(y_test, predictions_svm_mapped)
predictions_train_mapped = np.where(y == 0, -1, 1)
calcularValidacioCreuada(svm_model, X[top_correlated_variables], predictions_train_mapped)

Scores de validació creuada (recall): [0.0077821  0.01992032 0.01185771 0.01171875 0.        ]
Mitjana dels scores (recall): 0.01025577548045924
Scores de validació creuada (f1): [0.0005176  0.00126534 0.00079418 0.0007486  0.        ]
Mitjana dels scores (f1): 0.0006651426085821843


svm_model_tmp = OneClassSVM(nu=0.5)  # Adjust the nu parameter based on your dataset
svm_model_tmp.fit(X_train)

predictions_svm = svm_model_tmp.predict(X_test)
predictions_svm_mapped = np.where(predictions_svm == -1, 0, 1)

X, _ = make_blobs(n_samples=16000, centers=1, random_state=42)
plt.scatter(X[predictions_svm_mapped == 1, 0], X[predictions_svm_mapped == 1, 1], c='blue', label='Outliers', edgecolors='k', s=50)
plt.scatter(X[predictions_svm_mapped == 0, 0], X[predictions_svm_mapped == 0, 1], c='red', label='Inliers', edgecolors='k', s=50)
plt.title("One-Class SVM Outlier Detection")
plt.legend()
plt.show()


from sklearn.svm import OneClassSVM
svm_model = OneClassSVM(nu=0.5)  # Adjust the nu parameter based on your dataset
#svm_model.fit(X_resampled)
#predictions_svm = svm_model.pred
ict(X_test)
#predictions_svm_mapped = np.where(predictions_svm == -1, 0, 1)
#print("One-Class SVM Predictions:", predictions_svm_mapped)
#calcularQualitatResultats(y_test, predictions_svm_mapped)
predictions_train_mapped = np.where(y_res == 0, -1, 1)
calcularValidacioCreuada(svm_model, X_res[top_correlated_variables], predictions_train_mapped)

Scores de validació creuada (recall): [0.         0.         0.28290909 0.11745455 0.12472727]
Mitjana dels scores (recall): 0.10501818181818182
Scores de validació creuada (f1): [0.         0.         0.28106936 0.21021803 0.22179114]
Mitjana dels scores (f1): 0.14261570668686158


svm_model_resampling_tmp = OneClassSVM(nu=0.5)  # Adjust the nu parameter based on your dataset
svm_model_resampling_tmp.fit(X_resampled)
predictions_svm = svm_model_resampling_tmp.predict(X_test)
predictions_svm_mapped = np.where(predictions_svm == -1, 0, 1)
X, _ = make_blobs(n_samples=16000, centers=1, random_state=42)
plt.scatter(X[predictions_svm_mapped == 1, 0], X[predictions_svm_mapped == 1, 1], c='blue', label='Outliers', edgecolors='k', s=50)
plt.scatter(X[predictions_svm_mapped == 0, 0], X[predictions_svm_mapped == 0, 1], c='red', label='Inliers', edgecolors='k', s=50)
plt.title("One-Class SVM Outlier Detection")
plt.legend()
plt.show()


from tensorflow import keras
input_dim = X_train.shape[1]
encoding_dim = 32

mean_train = np.mean(X_train, axis=0)
std_train = np.std(X_train, axis=0)

X_train_normalized = (X_train - mean_train) / std_train
X_test_normalized = (X_test - mean_train) / std_train

autoencoder = keras.Sequential([
    keras.layers.InputLayer(input_shape=(input_dim,)),
    keras.layers.Dense(encoding_dim, activation='relu'),
    keras.layers.Dense(input_dim, activation='sigmoid')
])
autoencoder.compile(optimizer='adam', loss='mse')
autoencoder.fit(X_train_normalized, X_train_normalized, epochs=20, batch_size=64, shuffle=True, validation_data=(X_test_normalized, X_test_normalized))
reconstructed_instances = autoencoder.predict(X_test)
mse = np.mean(np.square(X_test_normalized - reconstructed_instances), axis=1)
threshold = np.percentile(mse, 94)
predictions_autoencoder = (mse > threshold).astype(int)

print("Autoencoder Predictions:", predictions_autoencoder)

calcularQualitatResultats(y_test, predictions_autoencoder)

Epoch 1/20
938/938 [==============================] - 2s 2ms/step - loss: 0.7436 - val_loss: 0.7069
Epoch 2/20
938/938 [==============================] - 2s 2ms/step - loss: 0.6777 - val_loss: 0.6897
Epoch 3/20
938/938 [==============================] - 2s 2ms/step - loss: 0.6665 - val_loss: 0.6819
Epoch 4/20
938/938 [==============================] - 2s 2ms/step - loss: 0.6610 - val_loss: 0.6777
Epoch 5/20
938/938 [==============================] - 2s 2ms/step - loss: 0.6578 - val_loss: 0.6748
Epoch 6/20
938/938 [==============================] - 2s 2ms/step - loss: 0.6557 - val_loss: 0.6726
Epoch 7/20
938/938 [==============================] - 2s 2ms/step - loss: 0.6540 - val_loss: 0.6707
Epoch 8/20
938/938 [==============================] - 2s 2ms/step - loss: 0.6525 - val_loss: 0.6694
Epoch 9/20
938/938 [==============================] - 2s 2ms/step - loss: 0.6515 - val_loss: 0.6687
Epoch 10/20
938/938 [==============================] - 2s 2ms/step - loss: 0.6508 - val_loss: 0.6682
Epoch 11/20
938/938 [==============================] - 2s 2ms/step - loss: 0.6503 - val_loss: 0.6677
Epoch 12/20
938/938 [==============================] - 2s 2ms/step - loss: 0.6499 - val_loss: 0.6674
Epoch 13/20
938/938 [==============================] - 2s 2ms/step - loss: 0.6495 - val_loss: 0.6671
Epoch 14/20
938/938 [==============================] - 2s 2ms/step - loss: 0.6492 - val_loss: 0.6667
Epoch 15/20
938/938 [==============================] - 2s 2ms/step - loss: 0.6489 - val_loss: 0.6663
Epoch 16/20
938/938 [==============================] - 2s 2ms/step - loss: 0.6480 - val_loss: 0.6652
Epoch 17/20
938/938 [==============================] - 2s 2ms/step - loss: 0.6477 - val_loss: 0.6651
Epoch 18/20
938/938 [==============================] - 2s 2ms/step - loss: 0.6475 - val_loss: 0.6649
Epoch 19/20
938/938 [==============================] - 2s 2ms/step - loss: 0.6474 - val_loss: 0.6645
Epoch 20/20
938/938 [==============================] - 2s 2ms/step - loss: 0.6472 - val_loss: 0.6647
500/500 [==============================] - 1s 1ms/step
Autoencoder Predictions: 0        0
1        0
2        0
3        0
4        0
        ..
15995    0
15996    0
15997    0
15998    0
15999    0
Length: 16000, dtype: int32
[[  325    50]
 [  635 14990]]
Precision: 0.339
Accuracy: 0.957
Recall: 0.867
F1: 0.487


X_test_array = X_test_normalized.to_numpy()

# Plotting
n_samples = min(3, X_test_array.shape[0])  # Choose the number of samples to visualize (e.g., 5)

plt.figure(figsize=(8, 4 * n_samples))

for i in range(n_samples):
    # Original Data
    plt.subplot(n_samples, 2, 2 * i + 1)
    plt.scatter(range(X_test_array.shape[1]), X_test_array[i], c='blue', marker='o', label='Original')
    plt.title(f'Original Data - Sample {i + 1}')
    plt.xlabel('Feature Index')
    plt.ylabel('Feature Value')

    # Reconstructed Data
    plt.subplot(n_samples, 2, 2 * i + 2)
    plt.scatter(range(X_test_array.shape[1]), reconstructed_instances[i], c='red', marker='x', label='Reconstructed')
    plt.title(f'Reconstructed Data - Sample {i + 1}')
    plt.xlabel('Feature Index')
    plt.ylabel('Feature Value')

plt.tight_layout()
plt.show()


from tensorflow import keras
input_dim = X_train.shape[1]
encoding_dim = 32

mean_train = np.mean(X_resampled, axis=0)
std_train = np.std(X_resampled, axis=0)

X_train_normalized = (X_resampled - mean_train) / std_train
X_test_normalized = (X_test - mean_train) / std_train

autoencoder = keras.Sequential([
    keras.layers.InputLayer(input_shape=(input_dim,)),
    keras.layers.Dense(encoding_dim, activation='relu'),
    keras.layers.Dense(input_dim, activation='sigmoid')
])
autoencoder.compile(optimizer='adam', loss='mse')
autoencoder.fit(X_train_normalized, X_train_normalized, epochs=20, batch_size=64, shuffle=True, validation_data=(X_test_normalized, X_test_normalized))
reconstructed_instances = autoencoder.predict(X_test)
mse = np.mean(np.square(X_test_normalized - reconstructed_instances), axis=1)
threshold = np.percentile(mse, 90)
predictions_autoencoder = (mse > threshold).astype(int)

print("Autoencoder Predictions:", predictions_autoencoder)

calcularQualitatResultats(y_test, predictions_autoencoder)

Epoch 1/20
157/157 [==============================] - 1s 5ms/step - loss: 0.8482 - val_loss: 0.6127
Epoch 2/20
157/157 [==============================] - 1s 3ms/step - loss: 0.6859 - val_loss: 0.5966
Epoch 3/20
157/157 [==============================] - 1s 4ms/step - loss: 0.6480 - val_loss: 0.5893
Epoch 4/20
157/157 [==============================] - 1s 3ms/step - loss: 0.6285 - val_loss: 0.5842
Epoch 5/20
157/157 [==============================] - 1s 3ms/step - loss: 0.6167 - val_loss: 0.5801
Epoch 6/20
157/157 [==============================] - 1s 3ms/step - loss: 0.6079 - val_loss: 0.5768
Epoch 7/20
157/157 [==============================] - 1s 3ms/step - loss: 0.6012 - val_loss: 0.5739
Epoch 8/20
157/157 [==============================] - 1s 3ms/step - loss: 0.5957 - val_loss: 0.5714
Epoch 9/20
157/157 [==============================] - 1s 3ms/step - loss: 0.5914 - val_loss: 0.5696
Epoch 10/20
157/157 [==============================] - 1s 3ms/step - loss: 0.5877 - val_loss: 0.5680
Epoch 11/20
157/157 [==============================] - 1s 3ms/step - loss: 0.5845 - val_loss: 0.5668
Epoch 12/20
157/157 [==============================] - 1s 3ms/step - loss: 0.5819 - val_loss: 0.5657
Epoch 13/20
157/157 [==============================] - 1s 3ms/step - loss: 0.5796 - val_loss: 0.5648
Epoch 14/20
157/157 [==============================] - 1s 3ms/step - loss: 0.5775 - val_loss: 0.5639
Epoch 15/20
157/157 [==============================] - 1s 3ms/step - loss: 0.5756 - val_loss: 0.5633
Epoch 16/20
157/157 [==============================] - 1s 3ms/step - loss: 0.5740 - val_loss: 0.5627
Epoch 17/20
157/157 [==============================] - 1s 3ms/step - loss: 0.5725 - val_loss: 0.5620
Epoch 18/20
157/157 [==============================] - 1s 3ms/step - loss: 0.5711 - val_loss: 0.5614
Epoch 19/20
157/157 [==============================] - 1s 3ms/step - loss: 0.5699 - val_loss: 0.5610
Epoch 20/20
157/157 [==============================] - 1s 3ms/step - loss: 0.5687 - val_loss: 0.5605
500/500 [==============================] - 1s 1ms/step
Autoencoder Predictions: 0        0
1        0
2        1
3        0
4        0
        ..
15995    0
15996    1
15997    0
15998    0
15999    0
Length: 16000, dtype: int32
[[  114   261]
 [ 1486 14139]]
Precision: 0.071
Accuracy: 0.891
Recall: 0.304
F1: 0.115


X_test_array = X_test_normalized.to_numpy()

# Plotting
n_samples = min(3, X_test_array.shape[0])  # Choose the number of samples to visualize (e.g., 5)

plt.figure(figsize=(8, 4 * n_samples))

for i in range(n_samples):
    # Original Data
    plt.subplot(n_samples, 2, 2 * i + 1)
    plt.scatter(range(X_test_array.shape[1]), X_test_array[i], c='blue', marker='o', label='Original')
    plt.title(f'Original Data - Sample {i + 1}')
    plt.xlabel('Feature Index')
    plt.ylabel('Feature Value')

    # Reconstructed Data
    plt.subplot(n_samples, 2, 2 * i + 2)
    plt.scatter(range(X_test_array.shape[1]), reconstructed_instances[i], c='red', marker='x', label='Reconstructed')
    plt.title(f'Reconstructed Data - Sample {i + 1}')
    plt.xlabel('Feature Index')
    plt.ylabel('Feature Value')

plt.tight_layout()
plt.show()


from pyod.models.hbos import HBOS
from sklearn.model_selection import train_test_split
from sklearn.metrics import confusion_matrix, classification_report

hbos_model = HBOS(contamination=0.06)  # You can adjust the contamination parameter
calcularValidacioCreuada(hbos_model, X[top_correlated_variables], y)

C:\Users\Ramon\anaconda3\Lib\site-packages\pyod\models\base.py:430: UserWarning: y should not be presented in unsupervised learning.
  warnings.warn(
C:\Users\Ramon\anaconda3\Lib\site-packages\pyod\models\base.py:430: UserWarning: y should not be presented in unsupervised learning.
  warnings.warn(
C:\Users\Ramon\anaconda3\Lib\site-packages\pyod\models\base.py:430: UserWarning: y should not be presented in unsupervised learning.
  warnings.warn(
C:\Users\Ramon\anaconda3\Lib\site-packages\pyod\models\base.py:430: UserWarning: y should not be presented in unsupervised learning.
  warnings.warn(
C:\Users\Ramon\anaconda3\Lib\site-packages\pyod\models\base.py:430: UserWarning: y should not be presented in unsupervised learning.
  warnings.warn(
C:\Users\Ramon\anaconda3\Lib\site-packages\pyod\models\base.py:430: UserWarning: y should not be presented in unsupervised learning.
  warnings.warn(

Scores de validació creuada (recall): [0.85992218 0.80079681 0.81422925 0.81640625 0.84078212]
Mitjana dels scores (recall): 0.8264273227308433
Scores de validació creuada (f1): [0.35964199 0.35989257 0.35982533 0.36828194 0.458492  ]
Mitjana dels scores (f1): 0.3812267647239174

C:\Users\Ramon\anaconda3\Lib\site-packages\pyod\models\base.py:430: UserWarning: y should not be presented in unsupervised learning.
  warnings.warn(
C:\Users\Ramon\anaconda3\Lib\site-packages\pyod\models\base.py:430: UserWarning: y should not be presented in unsupervised learning.
  warnings.warn(
C:\Users\Ramon\anaconda3\Lib\site-packages\pyod\models\base.py:430: UserWarning: y should not be presented in unsupervised learning.
  warnings.warn(
C:\Users\Ramon\anaconda3\Lib\site-packages\pyod\models\base.py:430: UserWarning: y should not be presented in unsupervised learning.
  warnings.warn(


hbos_model_tmp = HBOS(contamination=0.06)  # You can adjust the contamination parameter
hbos_model_tmp.fit(X_train)
predictions_hbos = hbos_model_tmp.predict(X_test)
classification_rep = classification_report(y_test, predictions_hbos)
print("Classification Report:")
print(classification_rep)
calcularQualitatResultats(y_test, predictions_hbos)
anomaly_scores = hbos_model.decision_function(X_test)
plt.figure(figsize=(8, 4))
plt.scatter(range(len(anomaly_scores)), anomaly_scores, c='red', marker='o', edgecolors='k', s=50)
plt.axhline(y=0, color='blue', linestyle='--', label='Decision Boundary')
plt.title('HBOS Anomaly Scores')
plt.xlabel('Data Point Index')
plt.ylabel('Anomaly Score')
plt.legend()
plt.show()

Classification Report:
              precision    recall  f1-score   support

           0       0.99      0.96      0.97     15625
           1       0.27      0.67      0.38       375

    accuracy                           0.95     16000
   macro avg       0.63      0.82      0.68     16000
weighted avg       0.97      0.95      0.96     16000

[[  253   122]
 [  696 14929]]
Precision: 0.267
Accuracy: 0.949
Recall: 0.675
F1: 0.382


from pyod.models.hbos import HBOS
from sklearn.model_selection import train_test_split
from sklearn.metrics import confusion_matrix, classification_report

hbos_model_resampling = HBOS(contamination=0.5)  # You can adjust the contamination parameter
calcularValidacioCreuada(hbos_model_resampling, X_res[top_correlated_variables], y_res)

Scores de validació creuada (recall): [0.         0.         0.78690909 0.93745455 0.92072727]
Mitjana dels scores (recall): 0.5290181818181818
Scores de validació creuada (f1): [0.         0.         0.78805535 0.96771772 0.95872775]
Mitjana dels scores (f1): 0.5429001651194381

C:\Users\Ramon\anaconda3\Lib\site-packages\pyod\models\base.py:430: UserWarning: y should not be presented in unsupervised learning.
  warnings.warn(
C:\Users\Ramon\anaconda3\Lib\site-packages\pyod\models\base.py:430: UserWarning: y should not be presented in unsupervised learning.
  warnings.warn(
C:\Users\Ramon\anaconda3\Lib\site-packages\pyod\models\base.py:430: UserWarning: y should not be presented in unsupervised learning.
  warnings.warn(
C:\Users\Ramon\anaconda3\Lib\site-packages\pyod\models\base.py:430: UserWarning: y should not be presented in unsupervised learning.
  warnings.warn(
C:\Users\Ramon\anaconda3\Lib\site-packages\pyod\models\base.py:430: UserWarning: y should not be presented in unsupervised learning.
  warnings.warn(
C:\Users\Ramon\anaconda3\Lib\site-packages\pyod\models\base.py:430: UserWarning: y should not be presented in unsupervised learning.
  warnings.warn(
C:\Users\Ramon\anaconda3\Lib\site-packages\pyod\models\base.py:430: UserWarning: y should not be presented in unsupervised learning.
  warnings.warn(
C:\Users\Ramon\anaconda3\Lib\site-packages\pyod\models\base.py:430: UserWarning: y should not be presented in unsupervised learning.
  warnings.warn(
C:\Users\Ramon\anaconda3\Lib\site-packages\pyod\models\base.py:430: UserWarning: y should not be presented in unsupervised learning.
  warnings.warn(
C:\Users\Ramon\anaconda3\Lib\site-packages\pyod\models\base.py:430: UserWarning: y should not be presented in unsupervised learning.
  warnings.warn(


hbos_model_tmp = HBOS(contamination=0.5)  # You can adjust the contamination parameter
hbos_model_tmp.fit(X_resampled)
predictions_hbos = hbos_model_tmp.predict(X_test)
classification_rep = classification_report(y_test, predictions_hbos)
print("Classification Report:")
print(classification_rep)
calcularQualitatResultats(y_test, predictions_hbos)
anomaly_scores = hbos_model.decision_function(X_test)
plt.figure(figsize=(8, 4))
plt.scatter(range(len(anomaly_scores)), anomaly_scores, c='red', marker='o', edgecolors='k', s=50)
plt.axhline(y=0, color='blue', linestyle='--', label='Decision Boundary')
plt.title('HBOS Anomaly Scores')
plt.xlabel('Data Point Index')
plt.ylabel('Anomaly Score')
plt.legend()
plt.show()

Classification Report:
              precision    recall  f1-score   support

           0       0.98      0.56      0.71     15625
           1       0.03      0.51      0.05       375

    accuracy                           0.56     16000
   macro avg       0.50      0.53      0.38     16000
weighted avg       0.96      0.56      0.70     16000

[[ 191  184]
 [6899 8726]]
Precision: 0.027
Accuracy: 0.557
Recall: 0.509
F1: 0.051

	class	aa_000	ab_000	ac_000	ad_000	ae_000	af_000	ag_000	ag_001	ag_002	ag_003	ag_004	ag_005	ag_006	ag_007	ag_008	ag_009	ah_000	ai_000	aj_000	ak_000	al_000	am_0	an_000	ao_000	ap_000	aq_000	ar_000	as_000	at_000	au_000	av_000	ax_000	ay_000	ay_001	ay_002	ay_003	ay_004	ay_005	ay_006	ay_007	ay_008	ay_009	az_000	az_001	az_002	az_003	az_004	az_005	az_006	az_007	az_008	az_009	ba_000	ba_001	ba_002	ba_003	ba_004	ba_005	ba_006	ba_007	ba_008	ba_009	bb_000	bc_000	bd_000	be_000	bf_000	bg_000	bh_000	bi_000	bj_000	bk_000	bl_000	bm_000	bn_000	bo_000	bp_000	bq_000	br_000	bs_000	bt_000	bu_000	bv_000	bx_000	by_000	bz_000	ca_000	cb_000	cc_000	ce_000	cf_000	cg_000	ch_000	ci_000	cj_000	ck_000	cl_000	cm_000	cn_000	cn_001	cn_002	cn_003	cn_004	cn_005	cn_006	cn_007	cn_008	cn_009	co_000	cp_000	cq_000	cr_000	cs_000	cs_001	cs_002	cs_003	cs_004	cs_005	cs_006	cs_007	cs_008	cs_009	ct_000	cu_000	cv_000	cx_000	cy_000	cz_000	da_000	db_000	dc_000	dd_000	de_000	df_000	dg_000	dh_000	di_000	dj_000	dk_000	dl_000	dm_000	dn_000	do_000	dp_000	dq_000	dr_000	ds_000	dt_000	du_000	dv_000	dx_000	dy_000	dz_000	ea_000	eb_000	ec_00	ed_000	ee_000	ee_001	ee_002	ee_003	ee_004	ee_005	ee_006	ee_007	ee_008	ee_009	ef_000	eg_000
30329	-0.992188	-0.125000	0.992188	-0.468750	-0.007812	-0.046875	-0.054688	-0.007812	-0.03125	-0.054688	-0.117188	-0.140625	-0.164062	0.765625	-0.023438	-0.132812	-0.031250	0.109375	-0.054688	-0.023438	-0.023438	-0.109375	-0.109375	0.226562	0.242188	-0.015625	-0.000000	-0.101562	-0.007812	-0.039062	-0.015625	0.992188	0.992188	-0.03125	-0.015625	-0.023438	-0.03125	-0.03125	-0.070312	-0.218750	-0.281250	0.992188	-0.015625	-0.046875	-0.054688	-0.031250	-0.117188	-0.093750	0.398438	-0.109375	-0.0625	-0.046875	-0.015625	0.625000	0.210938	-0.085938	-0.171875	-0.234375	-0.281250	-0.273438	-0.273438	-0.140625	-0.109375	0.148438	-0.070312	-0.140625	0.132812	-0.031250	0.109375	0.203125	-0.140625	0.085938	-0.500000	-0.570312	-0.484375	-0.500000	-0.539062	-0.812500	-0.796875	-0.796875	-0.632812	-0.125000	0.148438	0.148438	0.203125	-0.148438	-0.148438	-0.835938	-0.734375	0.210938	0.992188	-0.007812	0.960938	-0.015625	0.054688	-0.09375	0.531250	-0.109375	0.429688	-0.039062	-0.085938	-0.117188	-0.140625	0.109375	0.703125	-0.046875	-0.093750	-0.093750	-0.03125	-0.007812	-0.070312	0.148438	-0.085938	0.312500	0.070312	-0.132812	0.992188	0.062500	0.007812	0.351562	0.015625	-0.000000	-0.007812	0.992188	0.992188	0.343750	-0.195312	-0.046875	-0.09375	-0.039062	-0.226562	0.312500	0.390625	0.039062	-0.023438	-0.03125	-0.007812	-0.101562	-0.007812	-0.03125	-0.023438	-0.03125	0.062500	-0.015625	-0.062500	-0.054688	-0.164062	0.507812	0.937500	-0.265625	-0.226562	-0.203125	-0.140625	-0.023438	-0.03125	-0.078125	0.140625	0.187500	0.507812	0.539062	0.203125	0.054688	0.007812	-0.179688	-0.257812	-0.179688	-0.250000	-0.171875	-0.023438	-0.023438
44957	-0.992188	-0.398438	0.242188	-0.468750	-0.007812	-0.046875	-0.054688	-0.007812	-0.03125	-0.054688	-0.117188	-0.187500	-0.335938	-0.406250	-0.343750	-0.164062	-0.031250	-0.421875	-0.054688	-0.023438	-0.023438	-0.109375	-0.109375	-0.429688	-0.429688	-0.320312	-0.343750	-0.101562	-0.007812	-0.039062	-0.015625	-0.171875	-0.242188	-0.03125	-0.015625	-0.023438	-0.03125	-0.03125	-0.078125	-0.304688	-0.296875	-0.257812	-0.015625	-0.085938	-0.125000	-0.078125	-0.132812	-0.343750	-0.320312	-0.109375	-0.0625	-0.046875	-0.015625	-0.351562	-0.367188	-0.335938	-0.359375	-0.375000	-0.367188	-0.328125	-0.351562	-0.148438	-0.109375	-0.406250	-0.156250	-0.195312	-0.156250	-0.132812	-0.421875	-0.375000	-0.328125	-0.273438	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	-0.695312	-0.398438	-0.406250	-0.406250	-0.390625	-0.398438	-0.171875	-0.835938	-0.828125	-0.390625	-0.429688	-0.007812	-0.226562	-0.015625	-0.406250	-0.09375	-0.312500	-0.109375	-0.218750	-0.039062	-0.085938	-0.148438	-0.234375	-0.367188	-0.414062	-0.312500	-0.156250	-0.101562	-0.03125	-0.007812	-0.078125	-0.406250	-0.085938	-0.382812	-0.250000	-0.195312	-0.312500	-0.210938	-0.390625	-0.414062	-0.140625	-0.015625	-0.007812	-0.140625	-0.164062	-0.507812	-0.226562	-0.046875	-0.09375	-0.039062	-0.226562	-0.515625	-0.312500	-0.179688	-0.023438	-0.03125	-0.007812	-0.101562	-0.007812	-0.03125	-0.023438	-0.03125	-0.335938	-0.437500	-0.468750	-0.054688	-0.164062	-0.414062	-0.429688	-0.351562	-0.289062	-0.203125	-0.140625	-0.023438	-0.03125	-0.234375	-0.351562	-0.390625	-0.289062	-0.296875	-0.382812	-0.382812	-0.375000	-0.320312	-0.304688	-0.195312	-0.296875	-0.164062	-0.023438	-0.023438
30866	-0.992188	-0.007812	-0.289062	-0.468750	-0.007812	-0.046875	-0.054688	-0.007812	-0.03125	-0.054688	-0.117188	-0.179688	-0.085938	0.210938	0.164062	0.015625	-0.015625	-0.031250	-0.054688	-0.023438	-0.023438	-0.109375	-0.109375	-0.000000	-0.031250	-0.015625	0.070312	-0.101562	-0.007812	-0.039062	-0.015625	-0.039062	-0.078125	-0.03125	-0.015625	-0.023438	-0.03125	-0.03125	-0.078125	0.406250	-0.117188	-0.085938	-0.015625	0.281250	0.601562	0.273438	0.648438	0.359375	-0.250000	-0.109375	-0.0625	-0.046875	-0.015625	0.062500	0.101562	-0.007812	-0.046875	-0.093750	-0.140625	-0.078125	0.070312	-0.140625	-0.109375	-0.007812	0.070312	-0.179688	-0.093750	-0.085938	-0.031250	-0.054688	-0.046875	0.015625	-0.476562	-0.398438	-0.210938	-0.835938	-0.820312	-0.812500	-0.796875	-0.796875	0.632812	-0.007812	-0.007812	-0.007812	0.023438	-0.023438	-0.164062	0.812500	0.992188	0.023438	0.218750	-0.007812	-0.132812	-0.015625	0.000000	-0.09375	-0.062500	-0.109375	-0.218750	-0.039062	-0.085938	-0.148438	-0.156250	0.007812	0.226562	0.054688	-0.054688	-0.062500	-0.03125	-0.007812	-0.070312	-0.007812	-0.085938	0.296875	0.093750	-0.117188	-0.046875	-0.046875	0.085938	0.046875	0.164062	0.000000	-0.007812	0.000000	-0.093750	-0.468750	-0.179688	-0.046875	0.65625	-0.039062	-0.101562	0.195312	-0.046875	-0.148438	-0.023438	-0.03125	-0.007812	-0.101562	-0.007812	-0.03125	-0.023438	-0.03125	-0.015625	0.992188	0.992188	-0.054688	-0.164062	-0.101562	-0.132812	0.992188	0.992188	-0.203125	-0.140625	-0.023438	-0.03125	-0.210938	0.273438	0.265625	-0.046875	-0.062500	-0.039062	0.421875	0.992188	-0.234375	-0.312500	-0.195312	-0.304688	-0.171875	-0.023438	-0.023438
40447	-0.992188	-0.132812	-0.289062	0.992188	-0.007812	-0.046875	-0.054688	-0.007812	-0.03125	-0.054688	-0.117188	-0.179688	0.015625	-0.140625	-0.281250	-0.148438	-0.031250	-0.164062	-0.054688	-0.023438	-0.023438	-0.109375	-0.109375	-0.171875	-0.164062	-0.132812	-0.171875	-0.101562	-0.007812	-0.039062	-0.015625	0.195312	-0.023438	-0.03125	-0.015625	-0.023438	-0.03125	-0.03125	-0.078125	-0.328125	-0.296875	0.320312	-0.015625	-0.062500	-0.109375	-0.070312	-0.132812	-0.351562	0.031250	-0.109375	-0.0625	-0.046875	-0.015625	-0.226562	-0.234375	0.054688	0.296875	0.171875	-0.140625	-0.265625	-0.296875	-0.140625	-0.109375	-0.164062	-0.148438	-0.187500	-0.132812	-0.023438	-0.164062	-0.226562	-0.093750	-0.140625	-0.406250	-0.359375	-0.882812	-0.835938	-0.820312	-0.812500	-0.796875	-0.796875	-0.226562	-0.132812	-0.164062	-0.164062	-0.132812	-0.101562	-0.171875	-0.296875	-0.250000	-0.156250	-0.187500	-0.007812	-0.039062	-0.015625	-0.179688	-0.06250	-0.171875	-0.109375	0.296875	-0.039062	-0.085938	-0.148438	-0.062500	0.101562	-0.335938	-0.289062	-0.140625	-0.101562	-0.03125	-0.007812	-0.078125	-0.164062	-0.062500	-0.039062	-0.093750	-0.187500	-0.070312	-0.179688	-0.234375	0.437500	0.054688	0.007812	-0.007812	-0.093750	-0.015625	-0.046875	-0.203125	-0.046875	-0.09375	-0.039062	0.031250	-0.109375	-0.109375	-0.125000	-0.023438	-0.03125	-0.007812	-0.031250	-0.007812	-0.03125	-0.023438	-0.03125	-0.218750	-0.429688	-0.453125	-0.054688	-0.164062	-0.304688	-0.296875	0.312500	0.078125	-0.203125	-0.140625	-0.023438	-0.03125	-0.242188	-0.117188	-0.117188	-0.140625	-0.210938	-0.250000	-0.242188	-0.234375	-0.132812	0.359375	-0.007812	-0.242188	-0.171875	-0.023438	-0.023438
25580	-0.992188	-0.406250	0.015625	-0.468750	-0.007812	-0.046875	-0.054688	-0.007812	-0.03125	-0.054688	-0.117188	-0.187500	-0.335938	-0.421875	-0.351562	-0.164062	-0.031250	-0.429688	-0.054688	-0.023438	-0.023438	-0.109375	-0.109375	-0.437500	-0.437500	-0.320312	-0.343750	-0.101562	-0.007812	-0.039062	-0.015625	-0.171875	-0.257812	-0.03125	-0.015625	-0.023438	-0.03125	-0.03125	-0.078125	-0.328125	-0.304688	-0.257812	-0.015625	-0.085938	-0.132812	-0.078125	-0.132812	-0.351562	-0.328125	-0.109375	-0.0625	-0.046875	-0.015625	-0.367188	-0.375000	-0.343750	-0.367188	-0.375000	-0.367188	-0.328125	-0.351562	-0.148438	-0.109375	-0.414062	-0.156250	-0.195312	-0.156250	-0.132812	-0.429688	-0.375000	-0.328125	-0.281250	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	-0.890625	-0.406250	-0.414062	-0.414062	-0.398438	-0.406250	-0.171875	-0.992188	-0.992188	-0.398438	-0.445312	-0.007812	-0.250000	-0.015625	-0.414062	-0.09375	-0.328125	-0.109375	-0.218750	-0.039062	-0.085938	-0.148438	-0.234375	-0.375000	-0.421875	-0.312500	-0.156250	-0.101562	-0.03125	-0.007812	-0.078125	-0.414062	-0.085938	-0.390625	-0.265625	-0.195312	-0.320312	-0.210938	-0.398438	-0.460938	-0.179688	-0.023438	-0.007812	-0.156250	-0.171875	-0.523438	-0.242188	-0.046875	-0.09375	-0.039062	0.156250	-0.523438	-0.320312	-0.203125	-0.023438	-0.03125	-0.007812	-0.101562	-0.007812	-0.03125	-0.023438	-0.03125	-0.343750	-0.445312	-0.476562	-0.054688	-0.164062	-0.414062	-0.437500	-0.351562	-0.289062	-0.203125	-0.140625	-0.023438	-0.03125	-0.242188	-0.398438	-0.421875	-0.296875	-0.304688	-0.382812	-0.382812	-0.382812	-0.351562	-0.312500	-0.195312	-0.304688	-0.171875	-0.023438	-0.023438

	class	aa_000	ab_000	ac_000	ad_000	ae_000	af_000	ag_000	ag_001	ag_002	ag_003	ag_004	ag_005	ag_006	ag_007	ag_008	ag_009	ah_000	ai_000	aj_000	ak_000	al_000	am_0	an_000	ao_000	ap_000	aq_000	ar_000	as_000	at_000	au_000	av_000	ax_000	ay_000	ay_001	ay_002	ay_003	ay_004	ay_005	ay_006	ay_007	ay_008	ay_009	az_000	az_001	az_002	az_003	az_004	az_005	az_006	az_007	az_008	az_009	ba_000	ba_001	ba_002	ba_003	ba_004	ba_005	ba_006	ba_007	ba_008	ba_009	bb_000	bc_000	bd_000	be_000	bf_000	bg_000	bh_000	bi_000	bj_000	bk_000	bl_000	bm_000	bn_000	bo_000	bp_000	bq_000	br_000	bs_000	bt_000	bu_000	bv_000	bx_000	by_000	bz_000	ca_000	cb_000	cc_000	ce_000	cf_000	cg_000	ch_000	ci_000	cj_000	ck_000	cl_000	cm_000	cn_000	cn_001	cn_002	cn_003	cn_004	cn_005	cn_006	cn_007	cn_008	cn_009	co_000	cp_000	cq_000	cr_000	cs_000	cs_001	cs_002	cs_003	cs_004	cs_005	cs_006	cs_007	cs_008	cs_009	ct_000	cu_000	cv_000	cx_000	cy_000	cz_000	da_000	db_000	dc_000	dd_000	de_000	df_000	dg_000	dh_000	di_000	dj_000	dk_000	dl_000	dm_000	dn_000	do_000	dp_000	dq_000	dr_000	ds_000	dt_000	du_000	dv_000	dx_000	dy_000	dz_000	ea_000	eb_000	ec_00	ed_000	ee_000	ee_001	ee_002	ee_003	ee_004	ee_005	ee_006	ee_007	ee_008	ee_009	ef_000	eg_000
10009	-0.992188	-0.203125	0.539062	-0.468750	-0.007812	-0.046875	-0.054688	-0.007812	-0.031250	-0.054688	-0.117188	-0.179688	-0.250000	-0.070312	0.007812	0.062500	0.023438	-0.187500	-0.054688	-0.023438	-0.023438	-0.109375	-0.109375	-0.187500	-0.187500	-0.179688	-0.187500	-0.101562	-0.007812	-0.023438	-0.015625	0.445312	0.164062	-0.03125	-0.015625	-0.023438	-0.03125	-0.03125	0.070312	0.164062	-0.234375	-0.242188	-0.015625	-0.046875	-0.054688	-0.054688	-0.023438	-0.046875	-0.195312	-0.109375	-0.062500	-0.046875	-0.015625	-0.070312	-0.250000	-0.242188	-0.242188	-0.226562	-0.203125	-0.140625	0.187500	-0.125000	-0.109375	-0.187500	-0.148438	-0.195312	-0.132812	-0.062500	-0.187500	-0.195312	-0.195312	-0.140625	-0.414062	-0.554688	-0.148438	-0.132812	-0.125000	-0.117188	-0.109375	-0.109375	-0.812500	-0.203125	-0.187500	-0.187500	-0.164062	-0.140625	-0.156250	-0.992188	-0.984375	-0.164062	-0.070312	-0.007812	0.031250	-0.015625	-0.195312	-0.093750	-0.171875	-0.109375	-0.218750	-0.039062	-0.085938	-0.148438	-0.210938	-0.156250	-0.070312	-0.109375	-0.117188	-0.085938	-0.031250	-0.007812	-0.078125	-0.187500	-0.085938	-0.015625	-0.070312	-0.125000	-0.125000	-0.117188	-0.132812	-0.281250	-0.070312	-0.023438	-0.007812	0.242188	0.054688	-0.500000	-0.210938	-0.039062	0.234375	-0.039062	-0.226562	-0.140625	-0.117188	-0.125000	-0.023438	-0.03125	-0.007812	-0.101562	-0.007812	-0.03125	-0.023438	-0.03125	-0.171875	-0.000000	-0.171875	-0.054688	-0.164062	-0.164062	-0.250000	0.132812	0.031250	-0.125000	0.031250	-0.023438	-0.03125	-0.234375	-0.054688	-0.085938	-0.148438	-0.085938	-0.132812	-0.117188	-0.117188	-0.085938	-0.171875	-0.164062	-0.179688	-0.148438	-0.023438	-0.023438
15015	-0.992188	-0.390625	-0.031250	-0.468750	-0.007812	-0.046875	-0.054688	-0.007812	-0.031250	-0.054688	-0.117188	-0.179688	-0.335938	-0.398438	-0.312500	-0.140625	-0.031250	-0.414062	-0.054688	-0.015625	-0.023438	-0.109375	-0.109375	-0.421875	-0.421875	-0.304688	-0.335938	-0.101562	-0.007812	-0.039062	-0.015625	-0.054688	-0.156250	-0.03125	-0.015625	-0.023438	-0.03125	-0.03125	-0.078125	-0.281250	-0.296875	-0.265625	-0.015625	-0.101562	-0.125000	-0.070312	-0.125000	-0.328125	-0.320312	-0.109375	-0.062500	-0.046875	-0.015625	-0.343750	-0.351562	-0.335938	-0.359375	-0.375000	-0.367188	-0.328125	-0.351562	-0.148438	-0.109375	-0.398438	-0.148438	-0.195312	-0.156250	-0.132812	-0.414062	-0.367188	-0.312500	-0.257812	-0.960938	-0.960938	-0.882812	-0.835938	-0.820312	-0.812500	-0.796875	-0.796875	-0.234375	-0.390625	-0.398438	-0.398438	-0.382812	-0.398438	-0.171875	-0.531250	-0.531250	-0.382812	-0.398438	-0.007812	-0.203125	-0.015625	-0.398438	-0.093750	-0.296875	-0.109375	-0.218750	-0.039062	-0.085938	-0.148438	-0.234375	-0.359375	-0.406250	-0.289062	-0.156250	-0.101562	-0.031250	-0.007812	-0.078125	-0.398438	-0.085938	-0.460938	-0.250000	-0.195312	-0.296875	-0.203125	-0.390625	-0.398438	-0.132812	-0.007812	-0.007812	-0.085938	-0.132812	-0.492188	-0.242188	-0.046875	-0.093750	-0.039062	-0.046875	-0.500000	-0.289062	-0.171875	-0.023438	-0.03125	-0.007812	-0.101562	-0.007812	-0.03125	-0.023438	-0.03125	-0.328125	-0.437500	-0.468750	-0.054688	-0.164062	-0.398438	-0.414062	-0.351562	-0.289062	-0.203125	-0.140625	-0.023438	-0.03125	-0.226562	-0.351562	-0.367188	-0.273438	-0.289062	-0.375000	-0.375000	-0.367188	-0.320312	-0.304688	-0.195312	-0.304688	-0.171875	-0.023438	-0.023438
14062	-0.992188	-0.062500	-0.289062	0.992188	-0.007812	-0.046875	-0.054688	-0.007812	-0.031250	-0.054688	-0.117188	-0.171875	-0.281250	0.054688	0.937500	0.312500	-0.015625	-0.046875	-0.054688	-0.023438	-0.023438	-0.109375	-0.109375	0.007812	0.007812	-0.109375	-0.046875	-0.101562	-0.007812	-0.039062	-0.015625	0.523438	0.218750	-0.03125	-0.015625	-0.023438	-0.03125	-0.03125	-0.070312	-0.234375	-0.257812	0.609375	-0.015625	-0.023438	-0.046875	-0.054688	-0.070312	0.328125	-0.156250	-0.109375	-0.062500	-0.046875	-0.015625	0.023438	0.054688	0.062500	0.093750	0.062500	-0.046875	-0.101562	-0.078125	-0.148438	-0.109375	-0.031250	-0.132812	-0.187500	-0.125000	-0.085938	-0.046875	0.000000	-0.125000	-0.085938	-0.523438	-0.515625	-0.562500	-0.835938	-0.820312	-0.812500	-0.796875	-0.796875	0.062500	-0.062500	-0.031250	-0.031250	0.007812	0.007812	-0.171875	0.273438	0.375000	0.023438	0.906250	-0.007812	0.125000	-0.015625	-0.023438	-0.093750	0.015625	-0.109375	-0.218750	-0.039062	-0.085938	-0.148438	-0.179688	-0.312500	0.304688	0.687500	-0.000000	-0.054688	-0.031250	-0.007812	-0.078125	-0.031250	-0.085938	0.437500	0.093750	0.015625	0.039062	-0.046875	0.046875	-0.039062	0.039062	-0.015625	-0.007812	0.406250	0.078125	0.250000	-0.195312	-0.046875	-0.093750	-0.039062	0.054688	0.148438	0.101562	-0.023438	-0.023438	-0.03125	-0.007812	-0.101562	-0.007812	-0.03125	-0.023438	-0.03125	-0.054688	-0.203125	-0.101562	-0.054688	-0.164062	0.367188	0.554688	0.523438	0.195312	-0.203125	-0.140625	-0.023438	-0.03125	-0.171875	0.054688	0.203125	0.023438	0.085938	0.125000	0.093750	0.015625	-0.093750	-0.085938	-0.101562	0.164062	-0.148438	-0.023438	-0.023438
2287	0.992188	0.992188	-0.289062	-0.468750	-0.007812	-0.046875	-0.054688	-0.007812	-0.023438	0.992188	0.992188	0.992188	0.992188	0.906250	0.148438	0.007812	-0.023438	0.992188	0.054688	-0.023438	-0.023438	0.867188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	-0.007812	0.039062	-0.015625	0.992188	0.992188	-0.03125	-0.015625	-0.023438	-0.03125	-0.03125	-0.023438	0.992188	0.992188	-0.007812	-0.015625	0.710938	0.203125	0.062500	-0.101562	-0.296875	0.992188	0.992188	0.992188	-0.046875	-0.015625	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.882812	0.992188	0.992188	0.992188	0.992188	0.531250	0.546875	0.882812	0.859375	0.992188	0.992188	0.968750	0.992188	-0.460938	-0.343750	-0.414062	-0.515625	-0.398438	-0.039062	0.039062	-0.070312	-0.515625	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	-0.289062	-0.593750	0.992188	0.992188	-0.007812	-0.234375	-0.015625	0.992188	0.992188	0.992188	0.023438	0.992188	0.351562	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	-0.007812	-0.023438	0.992188	-0.085938	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.695312	-0.000000	-0.007812	-0.148438	-0.093750	-0.445312	-0.156250	-0.046875	-0.085938	-0.039062	-0.226562	-0.453125	0.992188	0.992188	-0.023438	-0.03125	-0.007812	0.992188	-0.007812	-0.03125	-0.023438	-0.03125	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	-0.023438	-0.03125	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	-0.195312	-0.171875	-0.023438	-0.023438
9207	-0.992188	-0.187500	-0.289062	-0.468750	-0.007812	-0.046875	-0.054688	-0.007812	-0.031250	-0.054688	-0.117188	-0.179688	-0.320312	-0.085938	0.187500	0.125000	-0.015625	-0.203125	-0.054688	-0.023438	-0.023438	-0.109375	-0.109375	-0.187500	-0.187500	-0.195312	-0.187500	-0.101562	-0.007812	-0.039062	-0.015625	-0.031250	-0.109375	-0.03125	-0.015625	-0.023438	-0.03125	-0.03125	-0.062500	-0.039062	-0.101562	-0.210938	-0.015625	-0.078125	-0.109375	-0.070312	-0.085938	0.070312	-0.265625	-0.109375	-0.062500	-0.046875	-0.015625	-0.203125	-0.234375	-0.226562	-0.210938	-0.164062	-0.109375	0.179688	0.445312	-0.148438	-0.109375	-0.195312	-0.148438	-0.195312	-0.156250	-0.085938	-0.203125	-0.226562	-0.171875	-0.187500	-0.429688	-0.320312	-0.117188	-0.093750	-0.093750	-0.085938	-0.078125	-0.078125	0.914062	-0.187500	-0.195312	-0.195312	-0.171875	-0.015625	-0.171875	0.992188	0.992188	-0.171875	0.085938	-0.007812	-0.109375	-0.015625	-0.195312	-0.093750	-0.171875	-0.109375	-0.218750	-0.039062	-0.085938	-0.148438	-0.234375	-0.320312	-0.031250	0.226562	-0.085938	-0.078125	-0.023438	-0.007812	-0.007812	-0.195312	-0.085938	-0.179688	-0.164062	-0.156250	-0.140625	-0.148438	-0.132812	-0.179688	-0.093750	-0.015625	-0.007812	0.046875	-0.101562	-0.078125	-0.242188	-0.046875	-0.046875	-0.039062	0.460938	-0.140625	-0.164062	-0.054688	-0.023438	-0.03125	-0.007812	-0.101562	-0.007812	-0.03125	-0.023438	-0.03125	-0.218750	0.109375	-0.101562	-0.054688	-0.164062	-0.164062	-0.117188	-0.351562	-0.289062	-0.203125	-0.140625	-0.023438	-0.03125	-0.195312	-0.203125	-0.226562	-0.156250	-0.132812	-0.101562	-0.125000	-0.156250	-0.187500	-0.171875	-0.140625	0.218750	0.062500	-0.023438	-0.023438

	class	aa_000	ab_000	ac_000	ad_000	ae_000	af_000	ag_000	ag_001	ag_002	ag_003	ag_004	ag_005	ag_006	ag_007	ag_008	ag_009	ah_000	ai_000	aj_000	ak_000	al_000	am_0	an_000	ao_000	ap_000	aq_000	ar_000	as_000	at_000	au_000	av_000	ax_000	ay_000	ay_001	ay_002	ay_003	ay_004	ay_005	ay_006	ay_007	ay_008	ay_009	az_000	az_001	az_002	az_003	az_004	az_005	az_006	az_007	az_008	az_009	ba_000	ba_001	ba_002	ba_003	ba_004	ba_005	ba_006	ba_007	ba_008	ba_009	bb_000	bc_000	bd_000	be_000	bf_000	bg_000	bh_000	bi_000	bj_000	bk_000	bl_000	bm_000	bn_000	bo_000	bp_000	bq_000	br_000	bs_000	bt_000	bu_000	bv_000	bx_000	by_000	bz_000	ca_000	cb_000	cc_000	cd_000	ce_000	cf_000	cg_000	ch_000	ci_000	cj_000	ck_000	cl_000	cm_000	cn_000	cn_001	cn_002	cn_003	cn_004	cn_005	cn_006	cn_007	cn_008	cn_009	co_000	cp_000	cq_000	cr_000	cs_000	cs_001	cs_002	cs_003	cs_004	cs_005	cs_006	cs_007	cs_008	cs_009	ct_000	cu_000	cv_000	cx_000	cy_000	cz_000	da_000	db_000	dc_000	dd_000	de_000	df_000	dg_000	dh_000	di_000	dj_000	dk_000	dl_000	dm_000	dn_000	do_000	dp_000	dq_000	dr_000	ds_000	dt_000	du_000	dv_000	dx_000	dy_000	dz_000	ea_000	eb_000	ec_00	ed_000	ee_000	ee_001	ee_002	ee_003	ee_004	ee_005	ee_006	ee_007	ee_008	ee_009	ef_000	eg_000
count	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000	76000.000000
mean	-0.956286	-0.123457	-0.068506	-0.204456	-0.007744	-0.032901	-0.039935	-0.006538	-0.025861	-0.040086	-0.073948	-0.096590	-0.114123	-0.100090	-0.087194	-0.053257	-0.018698	-0.128756	-0.035237	-0.019805	-0.021407	-0.061695	-0.061888	-0.126925	-0.126813	-0.114968	-0.111576	-0.063860	-0.007479	-0.025440	-0.014966	-0.054155	-0.081160	-0.028543	-0.013480	-0.020724	-0.026993	-0.026518	-0.038354	-0.081945	-0.097188	-0.102304	-0.013018	-0.033402	-0.046559	-0.027121	-0.046227	-0.101922	-0.106999	-0.068059	-0.044009	-0.035954	-0.012872	-0.103941	-0.108328	-0.109599	-0.108458	-0.105600	-0.100647	-0.093668	-0.102299	-0.068957	-0.064875	-0.126615	-0.068250	-0.077465	-0.061668	-0.058185	-0.128755	-0.120815	-0.109564	-0.104628	-0.166983	-0.160733	-0.153714	-0.151010	-0.150269	-0.151227	-0.148933	-0.151067	-0.128062	-0.123451	-0.126614	-0.126614	-0.119450	-0.114966	-0.080539	-0.121993	-0.114327	-0.119143	-0.000125	-0.099145	-0.007769	-0.069779	-0.015386	-0.125790	-0.064805	-0.108921	-0.080057	-0.091098	-0.029625	-0.055514	-0.086066	-0.101060	-0.110041	-0.102328	-0.077996	-0.065892	-0.058477	-0.021773	-0.007714	-0.038094	-0.126614	-0.063388	-0.108046	-0.069122	-0.088596	-0.098250	-0.093793	-0.112382	-0.094442	-0.019589	-0.009793	-0.007700	-0.036870	-0.059547	-0.136807	-0.115114	-0.033793	-0.039082	-0.028328	-0.038559	-0.137726	-0.095937	-0.057752	-0.019653	-0.025454	-0.005641	-0.064918	-0.007296	-0.028855	-0.021801	-0.029184	-0.112852	-0.094615	-0.105553	-0.036685	-0.094059	-0.110459	-0.110635	-0.107180	-0.087959	-0.102316	-0.073177	-0.020095	-0.024698	-0.095093	-0.108845	-0.111245	-0.097584	-0.090798	-0.104035	-0.098011	-0.093929	-0.088263	-0.102654	-0.087985	-0.084783	-0.067596	-0.019900	-0.018338
std	0.264488	0.368933	0.354247	0.559990	0.003686	0.108952	0.114069	0.032640	0.067743	0.108607	0.189024	0.257076	0.356217	0.383781	0.360956	0.217399	0.066004	0.381073	0.114209	0.047797	0.040711	0.192398	0.191147	0.388615	0.387402	0.315066	0.334439	0.180781	0.017944	0.092934	0.024368	0.242139	0.307676	0.045847	0.041715	0.045337	0.055067	0.056572	0.123435	0.344880	0.319074	0.302856	0.045139	0.162942	0.196780	0.143283	0.198141	0.366730	0.339008	0.180041	0.121645	0.092093	0.041163	0.348218	0.349829	0.328218	0.343321	0.355520	0.359694	0.334376	0.385969	0.235300	0.185761	0.369529	0.235658	0.265082	0.222901	0.214957	0.381072	0.349708	0.321543	0.290430	0.685287	0.713004	0.734811	0.746764	0.750918	0.754995	0.754578	0.757787	0.672921	0.368991	0.369582	0.369582	0.358962	0.367994	0.248009	0.773618	0.785222	0.358546	0.093746	0.448757	0.003660	0.233482	0.015508	0.371980	0.147374	0.323502	0.157989	0.283576	0.085434	0.155023	0.223568	0.289119	0.361280	0.387668	0.341521	0.208554	0.146235	0.079368	0.003717	0.144504	0.369582	0.127878	0.403157	0.289388	0.248334	0.328049	0.248167	0.364734	0.432127	0.227275	0.028360	0.008929	0.200351	0.227182	0.434096	0.282545	0.090405	0.160865	0.094027	0.274599	0.429119	0.325940	0.250826	0.057126	0.064071	0.031859	0.165466	0.019745	0.046531	0.039596	0.042373	0.328632	0.429458	0.462232	0.100253	0.246342	0.384647	0.403113	0.409089	0.345190	0.285210	0.224485	0.051746	0.072933	0.297537	0.355387	0.376722	0.307001	0.306367	0.356875	0.362312	0.363698	0.337173	0.321224	0.239546	0.363531	0.261067	0.052789	0.062205
min	-0.992188	-0.406250	-0.289062	-0.468750	-0.007812	-0.046875	-0.054688	-0.007812	-0.031250	-0.054688	-0.117188	-0.187500	-0.335938	-0.421875	-0.351562	-0.164062	-0.031250	-0.429688	-0.054688	-0.023438	-0.023438	-0.109375	-0.109375	-0.437500	-0.437500	-0.320312	-0.351562	-0.101562	-0.007812	-0.039062	-0.015625	-0.171875	-0.257812	-0.031250	-0.015625	-0.023438	-0.031250	-0.031250	-0.078125	-0.328125	-0.304688	-0.265625	-0.015625	-0.109375	-0.132812	-0.078125	-0.132812	-0.351562	-0.328125	-0.109375	-0.062500	-0.046875	-0.015625	-0.367188	-0.375000	-0.343750	-0.367188	-0.375000	-0.367188	-0.328125	-0.351562	-0.148438	-0.109375	-0.414062	-0.156250	-0.195312	-0.156250	-0.132812	-0.429688	-0.375000	-0.328125	-0.281250	-0.960938	-0.960938	-0.882812	-0.835938	-0.820312	-0.812500	-0.796875	-0.796875	-0.945312	-0.406250	-0.414062	-0.414062	-0.398438	-0.406250	-0.171875	-0.992188	-0.992188	-0.398438	-0.992188	-0.445312	-0.007812	-0.250000	-0.015625	-0.414062	-0.093750	-0.328125	-0.109375	-0.218750	-0.039062	-0.085938	-0.148438	-0.242188	-0.382812	-0.421875	-0.312500	-0.156250	-0.101562	-0.031250	-0.007812	-0.078125	-0.414062	-0.085938	-0.531250	-0.273438	-0.195312	-0.320312	-0.210938	-0.398438	-0.460938	-0.187500	-0.023438	-0.007812	-0.156250	-0.179688	-0.523438	-0.242188	-0.046875	-0.093750	-0.039062	-0.226562	-0.523438	-0.328125	-0.234375	-0.023438	-0.031250	-0.007812	-0.101562	-0.007812	-0.031250	-0.023438	-0.031250	-0.343750	-0.445312	-0.476562	-0.054688	-0.164062	-0.414062	-0.437500	-0.351562	-0.289062	-0.203125	-0.140625	-0.023438	-0.031250	-0.242188	-0.406250	-0.429688	-0.304688	-0.304688	-0.382812	-0.382812	-0.382812	-0.351562	-0.312500	-0.195312	-0.304688	-0.171875	-0.023438	-0.023438
25%	-0.992188	-0.398438	-0.289062	-0.468750	-0.007812	-0.046875	-0.054688	-0.007812	-0.031250	-0.054688	-0.117188	-0.179688	-0.335938	-0.421875	-0.351562	-0.164062	-0.031250	-0.421875	-0.054688	-0.023438	-0.023438	-0.109375	-0.109375	-0.429688	-0.429688	-0.312500	-0.343750	-0.101562	-0.007812	-0.039062	-0.015625	-0.171875	-0.250000	-0.031250	-0.015625	-0.023438	-0.031250	-0.031250	-0.078125	-0.328125	-0.296875	-0.257812	-0.015625	-0.093750	-0.125000	-0.078125	-0.132812	-0.351562	-0.320312	-0.109375	-0.062500	-0.046875	-0.015625	-0.359375	-0.375000	-0.335938	-0.359375	-0.375000	-0.367188	-0.328125	-0.351562	-0.148438	-0.109375	-0.406250	-0.156250	-0.195312	-0.156250	-0.132812	-0.421875	-0.375000	-0.320312	-0.273438	-0.625000	-0.648438	-0.882812	-0.835938	-0.820312	-0.812500	-0.796875	-0.796875	-0.742188	-0.398438	-0.406250	-0.406250	-0.390625	-0.398438	-0.171875	-0.882812	-0.882812	-0.390625	0.000000	-0.445312	-0.007812	-0.226562	-0.015625	-0.406250	-0.093750	-0.320312	-0.109375	-0.218750	-0.039062	-0.085938	-0.148438	-0.234375	-0.375000	-0.421875	-0.312500	-0.156250	-0.101562	-0.031250	-0.007812	-0.078125	-0.406250	-0.085938	-0.406250	-0.257812	-0.195312	-0.312500	-0.210938	-0.390625	-0.453125	-0.171875	-0.023438	-0.007812	-0.148438	-0.164062	-0.507812	-0.242188	-0.046875	-0.093750	-0.039062	-0.226562	-0.515625	-0.312500	-0.195312	-0.023438	-0.031250	-0.007812	-0.101562	-0.007812	-0.031250	-0.023438	-0.031250	-0.335938	-0.445312	-0.476562	-0.054688	-0.164062	-0.414062	-0.437500	-0.351562	-0.289062	-0.203125	-0.140625	-0.023438	-0.031250	-0.242188	-0.375000	-0.406250	-0.296875	-0.296875	-0.382812	-0.382812	-0.375000	-0.343750	-0.312500	-0.195312	-0.304688	-0.171875	-0.023438	-0.023438
50%	-0.992188	-0.195312	-0.289062	-0.468750	-0.007812	-0.046875	-0.054688	-0.007812	-0.031250	-0.054688	-0.117188	-0.179688	-0.281250	-0.187500	-0.265625	-0.156250	-0.031250	-0.195312	-0.054688	-0.023438	-0.023438	-0.109375	-0.109375	-0.195312	-0.195312	-0.210938	-0.210938	-0.101562	-0.007812	-0.039062	-0.015625	-0.156250	-0.210938	-0.031250	-0.015625	-0.023438	-0.031250	-0.031250	-0.078125	-0.273438	-0.234375	-0.234375	-0.015625	-0.078125	-0.109375	-0.062500	-0.125000	-0.328125	-0.250000	-0.109375	-0.062500	-0.046875	-0.015625	-0.187500	-0.187500	-0.187500	-0.187500	-0.187500	-0.203125	-0.218750	-0.343750	-0.148438	-0.109375	-0.195312	-0.148438	-0.187500	-0.140625	-0.132812	-0.195312	-0.203125	-0.210938	-0.195312	-0.445312	-0.445312	-0.414062	-0.429688	-0.460938	-0.484375	-0.554688	-0.796875	-0.343750	-0.195312	-0.195312	-0.195312	-0.179688	-0.171875	-0.171875	-0.304688	-0.335938	-0.179688	0.000000	-0.421875	-0.007812	-0.125000	-0.015625	-0.195312	-0.093750	-0.210938	-0.109375	-0.210938	-0.039062	-0.085938	-0.148438	-0.226562	-0.226562	-0.203125	-0.242188	-0.132812	-0.093750	-0.031250	-0.007812	-0.078125	-0.195312	-0.085938	-0.218750	-0.148438	-0.179688	-0.210938	-0.171875	-0.179688	-0.257812	-0.109375	-0.015625	-0.007812	-0.109375	-0.140625	-0.218750	-0.218750	-0.046875	-0.093750	-0.039062	-0.226562	-0.164062	-0.195312	-0.140625	-0.023438	-0.031250	-0.007812	-0.101562	-0.007812	-0.031250	-0.023438	-0.031250	-0.195312	-0.265625	-0.296875	-0.054688	-0.164062	-0.203125	-0.210938	-0.335938	-0.273438	-0.203125	-0.140625	-0.023438	-0.031250	-0.226562	-0.203125	-0.203125	-0.195312	-0.171875	-0.179688	-0.179688	-0.187500	-0.179688	-0.226562	-0.171875	-0.296875	-0.171875	-0.023438	-0.023438
75%	-0.992188	-0.070312	0.000000	-0.468750	-0.007812	-0.046875	-0.054688	-0.007812	-0.031250	-0.054688	-0.117188	-0.164062	-0.054688	0.062500	0.062500	-0.039062	-0.031250	-0.046875	-0.054688	-0.023438	-0.023438	-0.109375	-0.109375	-0.039062	-0.046875	-0.093750	-0.054688	-0.101562	-0.007812	-0.039062	-0.015625	-0.070312	-0.078125	-0.031250	-0.015625	-0.023438	-0.031250	-0.031250	-0.054688	0.054688	-0.039062	-0.109375	-0.015625	-0.046875	-0.070312	-0.046875	-0.070312	0.070312	-0.054688	-0.109375	-0.062500	-0.046875	-0.015625	-0.031250	-0.031250	-0.062500	-0.039062	-0.015625	-0.007812	-0.007812	0.039062	-0.140625	-0.109375	-0.062500	-0.117188	-0.109375	-0.085938	-0.101562	-0.046875	-0.054688	-0.078125	-0.093750	0.242188	0.656250	0.789062	0.835938	0.843750	0.851562	0.851562	0.859375	0.453125	-0.070312	-0.062500	-0.062500	-0.039062	-0.031250	-0.148438	0.750000	0.804688	-0.039062	0.000000	0.148438	-0.007812	-0.015625	-0.015625	-0.062500	-0.093750	-0.070312	-0.109375	-0.148438	-0.039062	-0.085938	-0.140625	-0.132812	-0.023438	0.054688	0.031250	-0.078125	-0.078125	-0.031250	-0.007812	-0.070312	-0.062500	-0.085938	0.023438	-0.031250	-0.117188	-0.054688	-0.109375	-0.031250	0.117188	0.039062	-0.007812	-0.007812	-0.015625	-0.070312	0.062500	-0.164062	-0.046875	-0.070312	-0.039062	0.078125	0.023438	-0.054688	-0.054688	-0.023438	-0.031250	-0.007812	-0.101562	-0.007812	-0.031250	-0.023438	-0.031250	-0.062500	0.125000	0.078125	-0.054688	-0.164062	0.015625	0.039062	-0.046875	-0.031250	-0.203125	-0.140625	-0.023438	-0.031250	-0.140625	-0.023438	-0.007812	-0.062500	-0.046875	-0.007812	0.015625	0.017578	0.007812	-0.054688	-0.101562	0.000000	-0.132812	-0.023438	-0.023438
max	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188	0.992188

Càrrega, neteja i anàlisi de dades¶

Model de classificació per predir si el sistema fallarà o no¶

Arbres de classificació¶

Random Forest Classifier¶

Entrenem amb les variables més correlacionades amb SAMPLING¶

XGBoost Classifier¶

Naive Bayes¶

Logistic regression¶

Support Vector Classifier¶

Xarxa neuronal¶

Model de detecció d'anomalies¶

Primer anàlisi de possibles anomalies¶

K-Means¶

DBSCAN¶

Models predictius¶

Isolation Forest¶

Local Outlier Factor¶

One-class SVM¶

Autoencoders¶

Histogram-based Outlier Score¶